index

Embodied Robotics Research Knowledge Base

Automated weekly digest covering the latest in embodied robotics research. Updated every Monday. Topics: VLAs, World Models, RL for Robotics.

---

Topics

• VLA — Vision-Language-Action Models
• WorldModels — World Models for Robotics
• RL-Robotics — Reinforcement Learning for Robotics

---

Papers & Releases

• nvidia-isaac-groot-n1-7 — NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots (2026-03-16) VLA
• gemini-robotics-er-1-6 — Gemini Robotics-ER 1.6: Enhanced Embodied Reasoning for Physical AI (2026-04-15) VLA
• vla-robotics-survey-datasets-benchmarks-data-engines — Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines (2026-04-24) VLA
• dreamdojo-generalist-robot-world-model — DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos (2026-02-06) WorldModels
• dreamzero-world-action-models-zero-shot-policies — World Action Models are Zero-shot Policies (DreamZero) (2026-02-17) WorldModels
• abot-physworld-interactive-world-foundation-model — ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment (2026-03-24) WorldModels
• simulation-distillation-world-model-sim-to-real — Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation (2026-03-16) WorldModels
• rl-token-bootstrapping-online-rl-vla — RL Token: Bootstrapping Online RL with Vision-Language-Action Models (2026-04-24) RL-Robotics
• large-reward-models-generalizable-online-robot-reward — Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models (2026-03-17) RL-Robotics
• towards-long-lived-robots-continual-learning-vla-rft — Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning (2026-02-11) RL-Robotics
• acot-vla-action-chain-of-thought-for-vla-models — ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models (2026-01-16) VLA
• abot-m0-vla-foundation-model-action-manifold-learning — ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning (2026-02-11) VLA
• dualcot-vla-visual-linguistic-chain-of-thought-parallel-reasoning — DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models (2026-03-23) VLA
• h-wm-hierarchical-world-model-task-motion-planning — H-WM: Robotic Task and Motion Planning Guided by Hierarchical World Model (2026-02-11) WorldModels
• chain-of-world-world-model-thinking-latent-motion — Chain of World: World Model Thinking in Latent Motion (2026-03-01) WorldModels
• hierarchical-planning-with-latent-world-models — Hierarchical Planning with Latent World Models (2026-04-03) WorldModels
• rlinf-co-sim-real-co-training-vla — RLinf-Co: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models (2026-02-13) RL-Robotics
• what-matters-sim-to-online-rl-real-robots — What Matters for Simulation to Online Reinforcement Learning on Real Robots (2026-02-23) RL-Robotics
• anticipation-vla-long-horizon-embodied-tasks-subgoal-generation — Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation (2026-05-11) VLA
• roboalign-test-time-reasoning-language-action-alignment-vla — RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models (2026-03-22) VLA
• being-h07-latent-world-action-model-egocentric-videos — Being-H0.7: A Latent World-Action Model from Egocentric Videos (2026-05-01) WorldModels
• roboalign-r1-multimodal-reward-alignment-robot-video-world-models — RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models (2026-05-05) WorldModels
• do-world-action-models-generalize-better-than-vlas-robustness-study — Do World Action Models Generalize Better than VLAs? A Robustness Study (2026-03-23) WorldModels
• mwm-mobile-world-models-action-conditioned-consistent-prediction — MWM: Mobile World Models for Action-Conditioned Consistent Prediction (2026-03-08) WorldModels
• mask-world-model-predicting-what-matters-robust-robot-policy-learning — Mask World Model: Predicting What Matters for Robust Robot Policy Learning (2026-04-21) WorldModels
• flashsac-fast-stable-off-policy-rl-high-dimensional-robot-control — FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control (2026-04-06) RL-Robotics
• alam-algebraically-consistent-latent-action-model-vla — ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models (2026-05-13) VLA
• vla-forget-vision-language-action-unlearning-embodied — VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models (2026-04-05) VLA
• from-pixels-to-tokens-latent-action-supervision-vla — From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models (2026-05-06) VLA
• defi-disentangled-robot-learning-forward-inverse-dynamics-pretraining — DeFI: Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining (2026-03-27) VLA
• world-model-for-robot-learning-comprehensive-survey — World Model for Robot Learning: A Comprehensive Survey (2026-04-30) WorldModels
• lawm-least-action-world-models-long-horizon-physical-consistency — LaWM: Least Action World Models for Long-Horizon Physical Consistency from Visual Observations (2026-05-08) WorldModels
• one-token-per-frame-visual-bandwidth-world-models-vla-policy — One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy (2026-05-08) WorldModels
• physically-native-world-models-hamiltonian-perspective — Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling (2026-05-01) WorldModels
• scaling-sim-to-real-rl-robot-vla-generative-3d-worlds — Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds (2026-03-19) RL-Robotics
• grounding-sim-to-real-generalization-dexterous-manipulation-vla — Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models (2026-03-24) RL-Robotics
• twinrl-vla-digital-twin-driven-rl-robotic-manipulation — TwinRL-VLA: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation (2026-02-10) RL-Robotics
• halo-unified-vla-embodied-multimodal-chain-of-thought-reasoning — HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning (2026-02-27) VLA
• ddp-wm-disentangled-dynamics-prediction-efficient-world-models — DDP-WM: Disentangled Dynamics Prediction for Efficient World Models (2026-02-02) WorldModels
• progressvla-progress-guided-diffusion-policy-vla-manipulation — ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation (2026-03-29) VLA
• atomvla-scalable-post-training-robotic-manipulation-predictive-latent-world-models — AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models (2026-03-10) VLA
• v-jepa-21-unlocking-dense-features-video-self-supervised-learning — V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning (2026-03-15) WorldModels
• sole-r1-video-language-reasoning-sole-reward-on-robot-rl — SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning (2026-03-28) RL-Robotics
• pi07-steerable-generalist-robotic-foundation-model — π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities (2026-04-16) VLA
• hex-humanoid-aligned-experts-cross-embodiment-whole-body-manipulation — HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation (2026-04-09) VLA
• echo-continuous-hierarchical-memory-vla-long-horizon — ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models (2026-05-01) VLA
• vla-continual-learning-real-world-without-forgetting — Can VLA Models Learn from Real-World Data Continually without Forgetting? (2026-05-26) RL-Robotics
• ahead-intercepting-the-future-latent-space-predictive-world-model-dynamic-vla — Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation (2026-06-01) VLA
• tempovla-speed-controllable-vla-policies — TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies (2026-06-04) VLA
• oscar-omni-embodiment-action-conditioned-world-model — OSCAR: Omni-Embodiment Action-Conditioned World Model for Robotics (2026-06-04) WorldModels
• robodream-compositional-world-models-robot-data-synthesis — RoboDream: Compositional World Models for Scalable Robot Data Synthesis (2026-06-01) WorldModels
• raw-dream-reinforcing-vlas-task-agnostic-world-models — RAW-Dream: Reinforcing VLAs in Task-Agnostic World Models (2026-05-12) WorldModels
• geosem-wam-geometry-semantic-aware-world-action-models — GeoSem-WAM: Geometry- and Semantic-Aware World Action Models (2026-06-02) WorldModels
• flowpro-reward-free-reinforced-finetuning-flow-matching-vlas — FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization (2026-06-03) RL-Robotics
• accerl-distributed-async-rl-world-model-framework-vla — AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for VLAs (2026-03-18) RL-Robotics
• seetraceact-visibility-aware-latent-planning-cross-embodiment-demos — SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos (2026-06-01) VLA
• tau0-wm-unified-video-action-world-model-agibot — τ₀-WM: A Unified Video-Action World Model for Robotic Manipulation (2026-06-01) WorldModels
• 3dthinkvla-latent-3d-priors-vla-co-training — 3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-training (2026-06-04) VLA
• affordancevla-affordance-aware-vla-action-generation — AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding (2026-06-05) VLA
• motionwam-foundation-world-action-model-humanoid-loco-manipulation — MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation (2026-06-08) WorldModels
• targeting-world-models-adversarial-robot-learning-pipelines — Targeting World Models to Compromise Robot Learning Pipelines (2026-06-08) WorldModels
• memoryvla-plus-plus-temporal-modeling-memory-imagination-vla — MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models (2026-06-08) VLA
• hierarchical-vla-agents-orchestrating-robot-policies — What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents (2026-06-09) VLA
• sarm2-stage-aware-reward-modeling-self-improving-robot-manipulation — SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation (2026-06-09) RL-Robotics
• making-foresight-actionable-agra-representation-alignment-wam — Making Foresight Actionable: Repurposing Representation Alignment in World Action Models (2026-06-10) WorldModels
• repwam-world-action-modeling-representation-visual-action-tokenizers — RepWAM: World Action Modeling with Representation Visual-Action Tokenizers (2026-06-11) WorldModels
• playworld-robot-world-models-autonomous-play — PlayWorld: Learning Robot World Models from Autonomous Play (2026-03-09) WorldModels
• world-action-verifier-self-improving-forward-inverse-asymmetry — World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry (2026-04-02) WorldModels
• weaver-effective-world-model-robotic-manipulation — WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation (2026-06-11) WorldModels
• world-models-robotic-manipulation-survey — World Models for Robotic Manipulation: A Survey (2026-06-01) WorldModels
• memorywam-efficient-world-action-modeling-persistent-memory — MemoryWAM: Efficient World Action Modeling with Persistent Memory (2026-06-18) WorldModels
• dexora-open-source-vla-bimanual-dexterity — Dexora: Open-source VLA for High-DoF Bimanual Dexterity (2026-05-18) VLA
• from-human-videos-to-robot-manipulation-survey — From Human Videos to Robot Manipulation: A Survey on Scalable VLA Learning with Human-Centric Data (2026-05-18) VLA
• agentic-vla-efficient-online-adaptation — Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models (2026-05-21) VLA
• labvla-grounding-vla-scientific-laboratories — LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories (2026-06-11) VLA
• thinkingvla-interleaved-vision-language-reasoning — ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation (2026-06-16) VLA
• finetuning-vla-fewer-layers — Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think (2026-06-18) VLA
• mpc-guided-rl-humanoid-locomotion-manipulation — Accelerating and Scaling MPC-Guided Reinforcement Learning for Humanoid Locomotion and Manipulation (2026-06-04) RL-Robotics
• rove-human-interventions-humanoid-manipulation-rl — ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning (2026-06-15) RL-Robotics
• playful-agentic-robot-learning-rats — Playful Agentic Robot Learning (RATs) (2026-06-17) RL-Robotics
• qwen-vla-unifying-vision-language-action-modeling — Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments (2026-05-29) VLA
• robots-need-more-than-vla-and-world-models — Robots Need More than VLA and World Models (2026-06-04) VLA
• geometric-action-model-robot-policy-learning — Geometric Action Model for Robot Policy Learning (2026-06-15) VLA
• la4vla-learning-to-act-without-seeing — LA4VLA: Learning to Act without Seeing via Language-Action Pretraining (2026-06-25) VLA
• nvidia-cosmos-3-omnimodal-world-models-physical-ai — Cosmos 3: Omnimodal World Models for Physical AI (2026-06-02) WorldModels
• veo-act-frontier-video-models-robot-manipulation — Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation? (2026-04-06) WorldModels
• oa-wam-object-addressable-world-action-model — OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation (2026-05-07) WorldModels
• flash-wam-modality-aware-distillation-world-action-models — Flash-WAM: Modality-Aware Distillation for World Action Models (2026-06-03) WorldModels
• aha-wam-asynchronous-horizon-adaptive-world-action-modeling — AHA-WAM: Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing (2026-06-10) WorldModels
• efficient-wam-1b-low-cost-future-imagination — Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination (2026-06-11) WorldModels
• kairos-native-world-model-stack-physical-ai — Kairos: A Native World Model Stack for Physical AI (2026-06-15) WorldModels
• imagewam-image-editing-vs-video-generation-world-action-models — ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing? (2026-06-19) WorldModels
• march-model-assisted-rl-humanoid-perceptive-control-sparse-footholds — MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds (2026-06-09) RL-Robotics
• loopvla-recurrent-refinement-vla-models — LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models (2026-05-09) VLA
• intentvla-short-horizon-intent-modeling-aliased-robot-manipulation — IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation (2026-05-14) VLA
• vla-pro-cross-task-procedural-memory-transfer — VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models (2026-05-29) VLA
• echo-memory-controlled-study-memory-action-world-models — Echo-Memory: A Controlled Study of Memory in Action World Models (2026-06-08) WorldModels
• himem-wam-hierarchical-memory-gated-world-action-models — HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation (2026-06-10) WorldModels
• apt-action-expert-pretraining-vla-instruction-generalization — APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies (2026-06-10) VLA
• rho-coding-agent-roboticist-neurosymbolic-policies — RHO: Your Coding Agent is Secretly a Roboticist (2026-06-16) RL-Robotics
• last-hd-latent-physical-reasoning-scalable-human-data — LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation (2026-06-23) VLA
• learning-action-priors-cross-embodiment-robot-manipulation — Learning Action Priors for Cross-embodiment Robot Manipulation (2026-06-26) VLA
• orca-world-foundation-model-multimodal-world-signals — Orca: The World is in Your Mind (2026-06-30) WorldModels
• aspire-agentic-skills-discovery-robotics — ASPIRE: Agentic Skills Discovery for Robotics (2026-06-30) RL-Robotics
• abot-m05-unified-mobility-manipulation-world-action-model — ABot-M0.5: Unified Mobility-and-Manipulation World Action Model (2026-07-01) WorldModels
• roboworld-neural-simulators-generalist-robot-policy-evaluation — RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation (2026-07-01) WorldModels
• neuro-symbolic-safety-guidance-vla-constrained-flow-matching — Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching (2026-07-01) VLA
• last-r1-reinforcing-manipulation-adaptive-physical-latent-reasoning — LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning (2026-04-28) RL-Robotics
• worldsample-closed-loop-real-robot-rl-world-modelling — WorldSample: Closed-loop Real-robot RL with World Modelling (2026-07-02) WorldModels
• one-demonstration-enough-real-world-robotic-rl — One Demonstration Is Enough for Real-World Robotic Reinforcement Learning (2026-07-02) RL-Robotics
• embodied-r15-evolving-physical-intelligence-foundation-models — Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models (2026-06-11) VLA
• taccorl-tactile-feedback-vla-simulation-cotraining — TacCoRL: Integrating Tactile Feedback into VLA via Simulation Co-Training and RL (2026-06-10) RL-Robotics
• policytrim-intrinsic-policy-efficiency-vla-rl — PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models (2026-06-26) VLA
• dvla-rl-reinforcement-learning-denoising-trajectories-discrete-diffusion-vla — dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion VLAs (2026-06-23) RL-Robotics
• from-world-models-to-world-action-models-tutorial-robotics — From World Models to World Action Models: A Concise Tutorial for Robotics (2026-07-01) WorldModels
• embodied-cpp-portable-inference-runtime-vla-wam — Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots (2026-07-02) VLA
• dswam-dual-system-world-action-foundation-model-fine-grained-manipulation — DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation (2026-07-06) WorldModels
• lerobot-v060-world-model-policies-open-robotics — LeRobot v0.6.0: Imagine, Evaluate, Improve — World Model Policies for Open Robotics (2026-07-07) VLA
• lift3d-vla-3d-geometry-dynamics-aware-vla — Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation (2026-07-07) VLA
• rynnworld-teleop-action-conditioned-world-model-digital-teleoperation — RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation (2026-07-07) WorldModels
• rynnworld-4d-4d-embodied-world-model-robotic-manipulation — RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation (2026-07-08) WorldModels
• lingbot-vla-20-open-source-cross-embodiment — LingBot-VLA 2.0: Open-Source Cross-Embodiment VLA for Universal Robot Control (2026-07-08) VLA
• drop-then-recovery-vla-redundancy-language-backbone — Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models? (2026-06-27) VLA
• vla-corrector-detect-correct-inference-adaptive-action-horizon — VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon (2026-07-01) VLA
• taco-tactile-world-model-vla-post-training — TACO: TActile World Model as a Self-COrrector for Scalable VLA Post-Training (2026-07-03) WorldModels
• harness-vla-memory-guided-agents-frozen-vla — Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents (2026-07-14) VLA
• dexverse-modular-benchmark-multi-task-dexterous-manipulation — DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation (2026-07-14) RL-Robotics
• xiaomi-robotics-u0-embodied-synthesis-world-foundation-model — Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model (2026-07-14) WorldModels
• nvidia-cosmos-3-edge-ondevice-world-model-jetson — NVIDIA Cosmos 3 Edge: On-Device World Foundation Model for Physical AI (2026-07-16) WorldModels
• never-too-late-for-force-reactive-force-injection-vla — Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection (2026-07-17) RL-Robotics
• reflex-real-time-vla-streaming-inference — Reflex: Real-Time VLA Control through Streaming Inference (2026-07-18) VLA
• expo-ft-sample-efficient-rl-finetuning-vla — EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models (2026-05-30) VLA
• legs-teleop-free-vla-humanoid-gaussian-splatting-world — LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World (2026-05-31) Humanoid
• boston-dynamics-atlas-training-humanoid-hard-work — Training a Humanoid Robot for Hard Work (2026-05-18) Humanoid
• ttt-vla-test-time-latent-prompt-optimization — TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models (2026-06-02) VLA
• mu0-scalable-3d-interaction-trace-world-model — μ0: A Scalable 3D Interaction-Trace World Model (2026-06-13) WorldModels
• enpire-agentic-robot-policy-self-improvement-real-world — ENPIRE: Agentic Robot Policy Self-Improvement in the Real World (2026-06-17) RL-Robotics
• retrieve-dont-retrain-vla-new-tasks-test-time — Retrieve, Don’t Retrain: Extending Vision Language Action Models to New Tasks at Test Time (2026-06-18) VLA
• force-efficient-vla-rl-value-calibrated-warmup — FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation (2026-06-24) VLA
• supervise-what-survives-geometry-guided-vla-adaptation-synthetic-video — Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos (2026-06-24) VLA
• humanoidumi-robot-free-demonstrations-humanoid-whole-body-manipulation — HumanoidUMI: Bridging Robot-Free Demonstrations and Humanoid Whole-Body Manipulation (2026-06-25) Humanoid
• sarl-semantic-reinforcement-learning-generalist-robot-policies — Adapting Generalist Robot Policies with Semantic Reinforcement Learning (SARL) (2026-06-26) RL-Robotics
• freeform-preference-learning-robotic-manipulation — Freeform Preference Learning for Robotic Manipulation (2026-06-26) RL-Robotics
• trust-your-instincts-confidence-driven-test-time-rl-vla — Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models (2026-06-29) RL-Robotics
• z1-efficient-rl-vla — Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models (2026-06-30) VLA
• gigaworld-1-world-models-robot-policy-evaluation — GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation (2026-07-02) WorldModels
• leveraging-offline-supervision-rl-large-scale-vla — Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models (2026-07-06) RL-Robotics
• temporal-ratio-video-action-generalization-gap — Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio (2026-07-08) WorldModels
• flowdagger-human-in-the-loop-latent-space-policy-adaptation — FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space (2026-07-09) VLA
• 1x-neo-hands-tendon-driven-dexterous-hand — 1X NEO Hands — 25-DoF tendon-driven, force-transparent dexterous hand (2026-07-09) Humanoid
• robottt-context-scaling-robot-policies — RoboTTT: Context Scaling for Robot Policies (2026-07-15) VLA
• rynnbrain-11-embodied-foundation-model — RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model (2026-07-20) VLA
• world-labs-acquires-scenix — World Labs Acquires SceniX (2026-07-21) WorldModels
• gemini-robotics-2-whole-body-intelligence — Gemini Robotics 2: whole-body VLA release for humanoids (2026-07-30) VLA
• nvidia-isaac-groot-lerobot-teleop-integration — NVIDIA Isaac GR00T comes to LeRobot: end-to-end humanoid VLA workflow with Isaac Teleop (2026-07-07) VLA
• what-to-ignore-what-to-react-visually-robust-rl-vla — What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models (2026-05-13) VLA
• hand-in-the-loop-dexterous-vla-intervention — Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention (2026-05-15) VLA
• learning-from-history-test-time-verification-adaptation-robotics — Learning From History: Test-Time Verification and Adaptation for Robotics (HAVE) (2026-07-06) VLA
• far-failure-aware-retry-test-time-recovery — FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement (2026-07-01) VLA
• axis-community-data-engine-robot-manipulation — AXIS: A Growable Community-Driven Data Engine for Scalable Robot Manipulation (2026-07-21) VLA
• furniturevla-bimanual-furniture-assembly — FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model (2026-07-01) VLA
• tau-touch-augmented-vla-future-visual-supervision — τ: Learning Touch-Augmented Vision-Language-Action Models from Future Visual Supervision (2026-07-28) VLA
• t3vf-test-time-training-visual-foresight-vla — T³VF: Test-Time Training for Visual Foresight Vision-Language-Action Models (2026-05-06) VLA
• test-time-scaling-world-action-models-geometric-verification — Test-Time Scaling for World Action Models via Zero-Shot Geometric Verification (2026-07-17) WorldModels
• decart-oasis-3-real-time-world-model — Decart Oasis 3: real-time interactive world model for driving/robotics simulation (2026-06-10) WorldModels
• world-labs-real-to-sim-to-real-robot-training — World Labs: Building Worlds That Train Robots (Real-to-Sim-to-Real) (2026-07-28) WorldModels
• definition-roadmap-world-models — A Definition and Roadmap for World Models (2026-07-07) WorldModels
• sword-style-robust-world-models-vla-post-training — Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training (2026-05-08) WorldModels
• learning-while-deploying-fleet-scale-rl-generalist-robot-policies — Learning while Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies (2026-05-01) RL-Robotics
• ohp-rl-online-human-preference-guidance-rl-manipulation — OHP-RL: Online Human Preference as Guidance in Reinforcement Learning for Robot Manipulation (2026-05-15) RL-Robotics
• pact-preference-calibrated-human-in-the-loop-rl — PACT: Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation (2026-06-03) RL-Robotics
• flow-reversal-steering-generalist-robot-policies — Improving Robotic Generalist Policies via Flow Reversal Steering (2026-06-13) RL-Robotics
• from-demonstrations-to-rewards-test-time-prompt-optimization-vlm-reward — From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models (2026-06-01) RL-Robotics
• rldx-1-multi-stream-action-transformer-humanoid — RLDX-1 Technical Report (2026-05-06) Humanoid
• oasis-sim-data-collection-humanoid-loco-manipulation — OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation (2026-06-07) Humanoid
• 1x-world-model-lab-launch — 1X launches humanoid robot World Model Lab (2026-06-04) Humanoid
• scaling-behavior-foundation-model-humanoid-robots — Scaling Behavior Foundation Model for Humanoid Robots (2026-07-16) Humanoid
• vlk-humanoid-loco-manipulation-synthetic-interactions — VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes (2026-06-30) Humanoid
• agibot-world-2026-rich-interaction-dataset — AgiBot World 2026 — Theme 2: “Rich Interaction” Dataset (2026-06-03) Humanoid
• ego2robot-scalable-robot-data-synthesis-egocentric-human-data — Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data (2026-08-03) VLA
• prigo-test-time-primitive-guidance-diffusion-flow-policies — PriGo: Test-Time Primitive Guidance to Diffusion and Flow Policies for Adaptive Robotic Manipulation (2026-07-07) VLA
• retrieve-then-steer-online-success-memory-test-time-adaptation-vla — Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs (2026-05-10) VLA
• wizard-robotic-policy-adaptation-weight-space-meta-learning — WIZARD: Robotic Policy Adaptation via Weight-Space Meta-Learning (2026-06-05) VLA
• set-supervised-diffusion-policy-action-chunking-corrections — Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections (2026-06-01) VLA
• vla-ad-offline-semantic-guidance-efficient-vla-distillation — Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation (VLA-AD) (2026-05-16) VLA
• retrieval-vla-training-free-in-context-adaptation — Retrieval-VLA: Training-Free In-Context Adaptation for Vision-Language-Action Models (2026-06-05) VLA
• dypes-vla-shared-dynamics-embodiment-specific-control-cross-embodiment — DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation (2026-08-06) VLA
• cross-embodiment-transfer-behavior-aligned-representations — Cross-Embodiment Transfer via Behavior-Aligned Representations (2026-07-30) VLA
• cloak-zero-shot-cross-embodiment-masking-end-effector — Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLA (2026-06-22) VLA
• primitivevla-reusable-motion-primitives-efficient-generalizable-manipulation — PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation (2026-05-28) VLA
• instant-fold-in-context-imitation-learning-deformable-manipulation — Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation (2026-06-04) VLA
• generalist-ai-gen1-thousand-hands-cross-embodiment-end-effector — Towards Machines with a Thousand Hands: GEN-1 Cross-Embodiment End-Effector Generalization (2026-07-22) VLA
• feedback-world-model-precise-guidance-diffusion-policy — Feedback World Model Enables Precise Guidance of Diffusion Policy (2026-05-20) WorldModels
• wayve-gaia-4-multimodal-world-models-closed-loop-simulation — GAIA-4: Multimodal World Models Powering Closed-Loop Simulation for Safe and Scalable Autonomy (2026-08-03) WorldModels
• deform360-massive-multiview-visuotactile-dataset-deformable-world-models — Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models (2026-07-10) WorldModels
• how-should-world-models-be-evaluated-decision-making-position — How Should World Models Be Evaluated for Embodied Decision-Making? (2026-06-28) WorldModels
• gauge-measurement-grounded-benchmark-physical-fidelity-simulation-video-world-models — GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models (2026-08-05) WorldModels
• vlaflow-unified-training-framework-co-training-future-latent-alignment — VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment (2026-07-02) WorldModels
• dream-tac-unified-tactile-world-action-model-contact-rich-manipulation — Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulation (2026-06-07) WorldModels
• geniworld-generalizable-interactive-world-model-visual-actions — GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions (2026-08-06) WorldModels
• omega-0-latent-predictive-world-action-model-concurrent-humanoid-loco-manipulation — ω₀: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation (2026-08-06) WorldModels
• rtcf-retrieve-in-time-correct-in-frequency-test-time-correction-vla — Retrieve in Time, Correct in Frequency (RTCF) (2026-08-05) RL-Robotics
• unintervene-agentic-intervention-efficient-real-world-rl — UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning (2026-06-15) RL-Robotics
• mapl-multi-objective-preference-learning-robot-locomotion — MAPL: Multi-Objective Preference Learning for Robot Locomotion (2026-06-29) RL-Robotics
• rarm-confidence-gated-progress-reward-modeling-rl-manipulation — RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation (2026-06-24) RL-Robotics
• densereward-dense-reward-learning-failure-synthesis-robotic-manipulation — DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation (2026-07-14) RL-Robotics
• progress-reward-modeling-robotic-learning-survey — Progress Reward Modeling for Robotic Learning: A Comprehensive Survey (2026-07-22) RL-Robotics
• torl-vla-tactile-guided-online-reinforcement-learning-contact-rich-manipulation — TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation (2026-06-10) RL-Robotics
• d-vla-high-concurrency-distributed-asynchronous-rl-framework — D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models (2026-05-13) RL-Robotics
• sp3o-reinforcement-learning-segment-preferences-without-reward-modeling — SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling (2026-08-02) RL-Robotics
• teleopit-full-embodiment-humanoid-teleoperation-system — Teleopit: A Full-Embodiment Humanoid Teleoperation System (2026-08-01) Humanoid
• thorarena-benchmarking-humanoid-physical-interaction-motion-force-demonstrations — ThorArena: Benchmarking Humanoid Physical Interaction with Human Motion-Force Demonstrations (2026-07-08) Humanoid
• heft-heavy-payload-full-size-humanoid-teleoperation-privileged-motion-guidance — HEFT: Heavy-Payload Full-size Humanoid Teleoperation with Privileged Motion Guidance and Windowed Payload Curriculum (2026-07-05) Humanoid
• humanoidarena-benchmarking-egocentric-hierarchical-whole-body-learning — HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning (2026-06-19) Humanoid
• light-loco-parkour-versatile-perceptive-whole-body-locomotion-multi-skill-distillation — Light-Loco-Parkour: Versatile Perceptive Whole-Body Locomotion via Multi-Skill Distillation (2026-08-02) Humanoid
• in-context-vla-agentic-tool-use-post-training — In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use (2026-08-05) VLA
• explicit-language-memory-long-horizon-planning-vla — Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models (2026-08-04) VLA
• handedit-embodiment-aware-image-editing-dataset-dexterous-hands — HandEdit: A Unified Embodiment-Aware Image-Editing Dataset and Benchmark for Dexterous Robot Hands (2026-08-12) VLA
• xiaomi-robotics-1-xr1-scaling-real-world-manipulation-pretraining — Xiaomi-Robotics-1 (XR-1): Scaling Real-World Manipulation Pretraining with Auto-Labeled UMI Data (2026-07-17) VLA
• crosstracer-hierarchical-cross-embodiment-navigation — CrossTracer: Hierarchical Cross-Embodiment Navigation via Pixel-Space Trace Proposal and Embodiment-Conditioned Correction (2026-08-08) VLA
• hymes-skills-in-weights-memory-in-code — Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation (HyMeS) (2026-08-10) VLA
• bora-offline-online-residual-adaptation-dexterous-vla — BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models (2026-05-28) RL-Robotics
• vista-vision-grounded-physics-validated-umi-data-vla — VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI Data for VLA Training (2026-06-04) RL-Robotics
• dexpie-stable-dexterous-policy-improvement-real-world-experience — DexPIE: Stable Dexterous Policy Improvement from Real-World Experience (2026-06-09) RL-Robotics
• midas-adaptation-generalist-robot-policies-minimal-data — MiDAS: Adaptation of Generalist Robot Policies with Minimal Data (2026-08-10) RL-Robotics
• scenesmith-agentic-scene-generation-robot-training-data — SceneSmith: Agentic Scene Generation for Scalable Robot Training Data (2026-07-13) RL-Robotics
• lila-wam-lightweight-latent-reasoning-world-action-model — LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation (2026-08-04) WorldModels
• lingbot-va-20-native-video-action-pretraining-generalizable-robot-control — Native Video-Action Pretraining for Generalizable Robot Control (LingBot-VA 2.0) (2026-07-09) WorldModels
• adawam-adaptive-multimodal-reasoning-world-action-models — Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning (AdaWAM) (2026-06-08) WorldModels
• vera-turning-video-models-into-generalist-robot-policies — Turning Video Models into Generalist Robot Policies (VERA) (2026-05-28) WorldModels
• efficient-sim-to-real-transfer-world-action-models-synthetic-priors — Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors (2026-06-30) WorldModels
• joyai-sim-simulation-interconversion-toolchain-embodied-data-pyramid — JoyAI-Sim: A Simulation-Enabled Interconversion Toolchain for the Embodied Data Pyramid (2026-06-17) WorldModels
• contactguard-pre-contact-execution-monitoring-latent-world-models — ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models (2026-08-13) WorldModels
• dreamx-phi-10-action-conditioned-video-world-model-manipulation — DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation (2026-08-13) WorldModels
• human-as-humanoid-zero-shot-learning-ego-exo-videos — Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments (2026-06-30) Humanoid
• skild-brain-10-omni-bodied-robot-foundation-model — Skild Brain 1.0: An Omni-Bodied Robot Foundation Model (2026-05-20) Humanoid
• figure-ai-scaling-helix-logistics — Scaling Helix: A New State of the Art in Humanoid Logistics (2026-07-01) Humanoid
• figure-03-autonomous-ladder-climb — Figure 03 Autonomous Ladder Climb (2026-08-01) Humanoid
• labimus-humanoid-dexterous-manipulation-chemical-laboratory — Labimus: A Simulation and Benchmark for Humanoid Dexterous Manipulation in Chemical Laboratory (2026-06-20) Humanoid
• simple-humanoid-loco-manipulation-simulation-benchmark — SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-Manipulation (2026-06-12) Humanoid
• eximo-vlm-guided-exploration-vla-policies — EXIMO: VLM Guided Exploration of VLA Policies (2026-08-20) VLA
• tau0-vla-hierarchical-robot-foundation-model-test-time-computation — τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation (2026-07-27) VLA
• stellavla-in-context-structured-demonstration-generalizable-vla — StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models (2026-08-01) VLA
• imagining-recovery-inference-time-counterfactual-realignment-vla — Imagining Recovery: Inference-Time Counterfactual Realignment for Vision-Language-Action Models (2026-08-14) VLA
• reflex-fast-predictive-vla-reaction-critical-manipulation — Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation (2026-08-16) VLA
• foca-future-oriented-conditioning-data-efficient-vla-adaptation — FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation (2026-06-18) VLA
• bridging-morphology-gap-intent-conditioned-fine-tuning-dexterous-vla — Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning (2026-06-10) VLA
• gen-15-embodied-foundation-models-one-shot-learners — GEN-1.5: Embodied Foundation Models are One-Shot Learners (2026-08-22) VLA
• hidden-in-plain-sight-diffusion-based-unrestricted-attacks-vla — Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models (2026-08-12) VLA
• egowam-world-action-models-beyond-pixels-egocentric-human-data — EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data (2026-07-08) WorldModels
• r2rdreamer-3d-aware-data-augmentation-spatially-generalized-manipulation — R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies (2026-06-15) WorldModels
• halo-wa-hybrid-attention-latent-guided-online-rl-world-action-models — HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models (2026-07-05) WorldModels
• wh0-generative-world-models-scalable-egocentric-hand-manipulation-data — Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data (2026-06-30) WorldModels
• wla-0-world-language-action-model-unified-world-modeling — World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis (2026-06-04) WorldModels
• paiworld-3d-consistent-world-foundation-model-manipulation — PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation (2026-06-16) WorldModels
• physisforcing-physics-reinforced-world-simulator-manipulation — PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation (2026-06-26) WorldModels
• dim-wam-world-action-modeling-diverse-historical-event-memory — DIM-WAM: World-Action Modeling with Diverse Historical Event Memory (2026-06-26) WorldModels
• temporal-grpo-beyond-trajectory-level-credit-vla-rl — Temporal GRPO: Beyond Trajectory-Level Credit in Vision-Language-Action Reinforcement Learning (2026-08-17) RL-Robotics
• recovla-vlm-guided-reward-compilation-failure-recovery-vla — ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies (2026-06-08) RL-Robotics
• score-support-constrained-rl-real-world-policy-improvement — Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience (SCORE) (2026-06-25) RL-Robotics
• robot-self-improvement-human-video-dynamics-models — Robot Self-Improvement via Human-Video Dynamics Models (2026-06-19) RL-Robotics
• regrind-minimalist-retargeting-guided-rl-dexterous-manipulation — REGRIND: A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation (2026-07-13) RL-Robotics
• toward-certified-functional-safety-industrial-humanoid-robots — Toward Certified Functional Safety for Industrial Humanoid Robots: The Fail-Passive Gap and a Feasibility Study (2026-08-02) Humanoid
• whole-body-planning-humanoids-confined-spaces-self-collision-avoidance — Whole-Body Planning for Humanoids Navigating Confined Spaces via Self-Collision Avoidance References (2026-08-10) Humanoid
• humantracker-comprehensive-human-aligned-motion-tracking-benchmark — HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark (2026-08-13) Humanoid
• noitom-hiphi-617-hour-high-precision-human-motion-dataset — Noitom Robotics Releases HiPHI: A 617-Hour High-Precision Human Motion Dataset (2026-08-19) Humanoid
• adapt-humanoid-robots-professional-style-tennis — AdaPT: Humanoid Robots Learn Professional-Style Tennis (2026-08-21) Humanoid
• unitree-superman-humanoid-record-jump-sprint-speed — Unitree Unveils “Superman” Humanoid with Record Jump and Sprint Speed (2026-08-18) Humanoid
• agility-robotics-digit-v5 — Agility Robotics Unveils Digit V5 (2026-08-10) Humanoid
• synthicl-scalable-in-context-imitation-learning-synthetic-data — SynthICL: Scalable In-context Imitation Learning with Synthetic Data (2026-06-08) VLA
• e-tts-embodied-test-time-scaling-framework-robotic-manipulation — E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation (2026-06-27) VLA
• self-improving-vla-selected-diffusion-noise-spurious-robust-action — Self-Improving VLA Policies: Selected Diffusion Noise for Spurious-Robust Action Smoothing (2026-06-12) VLA
• logic-vla-temporal-logic-conditioned-vision-language-action-model — Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model (2026-08-20) VLA
• vane-reliable-test-time-training-vla-future-visual-representation — VANE: Reliable Test-Time Training for VLA Models via Future Visual Representation Prediction (2026-08-09) VLA
• robosynchallenge-mastering-real-world-dexterity-synthesized-manipulation-skills — RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills (2026-08-12) VLA
• elastic-efficiently-learning-adaptively-scale-test-time-compute — ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies (2026-06-30) VLA
• g05-galaxea-autoregressive-stream-robot-reasoning-action — G0.5 (Galaxea): One Autoregressive Stream for Robot Reasoning and Action (2026-08-11) VLA
• ervla-revisiting-embodied-chain-of-thought-generalizable-robot-manipulation — Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation (2026-06-03) VLA
• robodojo-unified-sim-real-benchmark-generalist-robot-manipulation — RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies (2026-07-04) VLA
• active-real-world-factor-based-evaluation-generalist-robot-policies — Active Real-World Factor-Based Evaluation for Generalist Robot Policies (2026-07-16) VLA
• univiewvla-unified-multiview-vision-language-action-world-modeling — UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling (2026-06-21) VLA
• baton-long-horizon-robot-manipulation-agentic-subtask-exploration — Don’t Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory (2026-08-17) VLA
• ucag-p-unified-camera-centric-action-geometry-pretraining — One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulation (2026-08-26) VLA
• streampi-streaming-multimodal-temporal-modeling-vla — StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models (2026-08-26) VLA
• muvla-recurrent-memory-partially-observable-manipulation-vla — μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models (2026-06-12) VLA
• revisiting-parameter-redundancy-vla-vlm-to-vla-adaptation — Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation (2026-06-30) VLA
• wam-ttt-steering-world-action-models-watching-human-play-test-time — WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time (2026-07-09) WorldModels
• zero-wam-in-context-world-action-modeling-human-videos — Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization (2026-08-26) WorldModels
• wall-ss-scaling-long-horizon-world-models-next-scale-autoregression — WALL-SS: Scaling Long-horizon World Models via Next-Scale Autoregression (2026-08-26) WorldModels
• clap-cross-embodiment-video-world-models-zero-shot-physical-simulators — CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators (2026-08-27) WorldModels
• phizero-world-model-physical-language — PhiZero: A World Model Built Around Physical Language (2026-07-30) WorldModels
• graphop-wm-world-models-morphology-parameter-generalization — Graph-Operator World Models for Morphology-Parameter Generalization in Continuous Control (2026-08-21) WorldModels
• maskwam-unifying-mask-prompting-prediction-world-action-models — MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models (2026-06-16) WorldModels
• r3-training-robots-reason-natural-language-reinforcement-learning — R³: Training Robots to Reason in Natural Language via Reinforcement Learning (2026-08-26) RL-Robotics
• beyond-imitation-self-improving-robot-policies-off-policy-q-planning — Beyond Imitation: Self-Improving Robot Policies via Off-Policy Q-Planning (2026-08-21) RL-Robotics
• rynnvalue-scaling-robotic-value-foundation-models-temporal-distance — RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance (2026-08-10) RL-Robotics
• dipod-diffusion-policy-optimization-without-drifting-apart — DiPOD: Diffusion Policy Optimization without Drifting Apart (2026-06-11) RL-Robotics
• vlm-pbrs-automating-potential-based-reward-shaping-vlm-guidance — Automating Potential-based Reward Shaping with Vision Language Model Guidance (2026-06-25) RL-Robotics
• humanoid-dart-diffusion-guided-augmentation-loco-manipulation — Humanoid-DART: Humanoid Loco-Manipulation using Diffusion-guided Augmentation through Relabeling and Tracking (2026-06-25) Humanoid
• deed-data-efficient-post-training-retail-humanoid-vla — Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids (2026-07-22) Humanoid
• skild-s1-in-context-learning-robotics — Skild AI: Introducing S1 — In-Context Learning for Robotics (2026-08-25) Humanoid
• figure-ai-index-crowdsourced-human-video-data-platform — Figure AI: Index — Crowdsourced Human Video Data Platform (2026-08-26) Humanoid
• wolf-vla-whole-body-humanoid-optimal-locomotion-framework — WOLF-VLA: Whole-Body Humanoid Optimal Locomotion Framework for Vision-Language-Action Learning (2026-06-28) Humanoid
• golem-modular-humanoid-autonomy-ev-battery-disassembly — GOLEM: Modular Humanoid Autonomy Towards Electric Vehicle Battery Disassembly (2026-08-21) Humanoid
• xiaomi-second-generation-humanoid-tieda-debut — Xiaomi’s Second-Generation Humanoid Robot (Tieda) Debuts at WRC 2026 (2026-08-19) Humanoid
• handoff-humanoid-agentic-task-space-whole-body-control-distilled-teachers — HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers (2026-06-04) Humanoid
• coordex-coordinating-body-hand-priors-dexterous-loco-manipulation — CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation (2026-06-22) Humanoid
• data-standards-humanoid-robotics-missing-infrastructure — Data Standards for Humanoid Robotics: The Missing Infrastructure for Physical AI (2026-06-18) Humanoid
• agibot-world-2026-theme-3-reinforcement-learning-dataset — AgiBot World 2026 — Theme 3: Reinforcement Learning Dataset (2026-08-06) Humanoid
• haf-adapting-generalist-vlas-humanoid-whole-body-loco-manipulation — HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL (2026-08-17) Humanoid
• fetchman-visual-humanoid-loco-manipulation-simulated-experiences — FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences (2026-08-17) Humanoid
• adapt-agile-diffusion-action-priors-text-driven-humanoid-control — ADAPT: Agile Diffusion Action Priors for Robust and Steerable Online Text-Driven Humanoid Control (2026-09-01) Humanoid
• robo-valuerl-reliable-value-estimation-offline-to-online-rl — Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning (2026-07-10) RL-Robotics
• rl-bootstrapping-openvla-oft-novel-robot-embodiment — RL-Only Bootstrapping of OpenVLA-OFT for a Novel Cable-Driven Robot Embodiment (2026-08-02) RL-Robotics
• efficient-real-world-online-rl-centralized-training-critic-decomposition — Efficient Real-World Online RL for Robot Manipulation via Centralized Training and Critic Decomposition (2026-08-10) RL-Robotics
• facet-0-robotic-foundation-model-contact-rich-precise-manipulation — Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation (2026-09-01) RL-Robotics
• xr-2-scaling-bimanual-household-manipulation-1500-hours — Scaling Bimanual Household Manipulation from 1,500 Hours of Demonstrations to On-Policy Corrections (2026-09-03) VLA
• zeta-controlled-study-zero-shot-cross-embodiment-vla-transfer — ZETA: A Controlled Study of Zero-Shot Cross-Embodiment VLA Transfer for Tabletop Manipulation (2026-09-02) VLA
• lavla-latent-cluster-analysis-vision-language-action-models — Latent Cluster Analysis for Vision-Language-Action Models (2026-09-02) VLA
• toward-unified-robot-learning-representation-vla-world-models — Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models (2026-09-03) VLA
• robotok-internet-scale-data-engine-human-demonstration-retrieval — RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning (2026-09-02) VLA
• driving-vla-zero-shot-transfer-across-embodiments — Towards Zero-Shot Transfer Across Embodiments For Driving VLAs (2026-09-02) VLA
• world-labs-atlas-omni-world-model-spatial-intelligence — Atlas: An Omni World Model for Spatial Intelligence (2026-09-01) WorldModels
• wm-loco-world-model-augmented-visual-locomotion-humanoids-foothold-constrained-terrain — World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain (2026-09-01) WorldModels
• modeling-what-changes-sparse-residual-world-models-object-centric-manipulation — Modeling What Changes: Sparse, Residual World Models for Object-Centric Manipulation (2026-09-02) WorldModels
• veriphy-agentic-physical-reasoning-world-model-evaluation-refinement — VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement (2026-09-03) WorldModels
• wise-world-model-guided-imagination-scheduling-vla-post-training — WISE: World-model-guided Imagination Scheduling for Efficient Post-training of VLA Models (2026-09-03) WorldModels
• robotacdex-dexterous-visual-tactile-action-dataset-humanoid-manipulation — RoboTacDex: A Dexterous Visual-Tactile-Action Dataset for Humanoid Manipulation (2026-06-30) Humanoid
• dreamsteer-latent-world-models-can-steer-vla-policies-during-deployment-without-any-finetuning — DreamSteer: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning (2026-07-03) WorldModels
• sg-wam-self-guided-world-modeling-in-geometry-aware-policy-space — SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space (2026-08-02) WorldModels
• look-where-it-matters-adaptive-visual-refinement-vla — Look Where It Matters: Adaptive Visual Refinement for Vision-Language-Action Models (2026-08-03) VLA
• atlasvla-persistent-world-ego-state-modeling — AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models (2026-08-07) VLA
• lost-in-reconstruction-salt-action-tokenizer-language-alignment — Lost in Reconstruction: Aligning Action Representations with Language in Vision-Language-Action Models (2026-08-11) VLA
• q-learning-with-world-models — Q-Learning With World Models (2026-08-17) WorldModels
• v-link-recovering-lost-visual-representations-action-dit — V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models (2026-08-25) VLA
• phr-vla-planning-horizon-reasoning — PHR-VLA: Planning Horizon Reasoning for Vision-Language-Action Models (2026-08-27) VLA
• ihmc-fast-resilient-adaptable-loco-manipulation-behaviors — A System for Fast, Resilient, and Adaptable Loco-Manipulation Behaviors on Humanoid Robots (2026-09-01) Humanoid
• humanoid-safe-stop-learned-stoppability-value — Humanoid Safe Stop via Learned Stoppability Value (2026-09-02) Humanoid
• solarwm-open-data-and-scalable-training-for-long-horizon-video-world-models — SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models (2026-09-02) WorldModels
• spatially-aware-world-action-model-via-geometric-latent-diffusion — Spatially Aware World Action Model via Geometric Latent Diffusion (2026-09-02) WorldModels
• vla-precision-asymmetric-co-bootstrapping-online-rl — VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models (2026-09-04) VLA
• learning-to-use-imagination-progress-conditioned-future-utilization-for-world-action-models — Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models (2026-09-06) WorldModels
• openwam-an-open-modular-exploration-towards-systematic-world-action-model-pretraining — OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining (2026-09-07) WorldModels
• decal-physically-grounded-dexterous-vla-contact-aware-latent-co-imagination — DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imagination (2026-09-08) VLA
• worldagen-unified-state-action-prediction-with-test-time-world-model-training — WorldAgen: Unified State-Action Prediction with Test-Time World Model Training (2026-09-08) WorldModels
• assembling-two-parts-in-one-hand — Assembling Two Parts in One Hand (2026-09-09) RL-Robotics
• beyond-noise-steering-dual-latent-space-reinforcement-learning-for-generative-robot-policy — Beyond Noise Steering: Dual-Latent Space Reinforcement Learning for Generative Robot Policy (2026-09-10) RL-Robotics
• function-preserving-data-generation-real-to-sim-to-real — Function-Preserving Data Generation for Zero-Shot Real-to-Sim-to-Real Manipulation (2026-09-16) VLA
• ra-vla-retrieval-augmented-vla-test-time-adaptation — RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation (2026-08-26) VLA
• unitree-unifolm-wla-10-open-source-humanoid-foundation-model — Unitree UnifoLM-WLA-1.0: Fully Open-Sourced Humanoid Foundation Model (2026-09-10) VLA
• gemini-robotics-er-2 — Gemini Robotics ER 2 (2026-07-30) VLA
• behavior-prompting-policy-demonstrations-as-prompts — Behavior Prompting Policy: Demonstrations as Prompts for Manipulation (2026-06-29) VLA
• semivla-semi-supervised-vision-language-action-model — SemiVLA: Semi-Supervised Vision-Language-Action Model (2026-06-19) VLA
• one-demo-worth-thousand-trajectories-action-view-augmentation — One Demo is Worth a Thousand Trajectories: Action-View Augmentation for Visuomotor Policies (2026-06-17) VLA
• eventvla-event-driven-visual-evidence-memory — EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies (2026-06-29) VLA
• event-vla-action-conditioned-event-fusion-robust-vla — Event-VLA: Action-Conditioned Event Fusion for Robust Vision-Language-Action Model (2026-06-28) VLA
• foresightsafety-vla-unified-diagnostic-safety-benchmark — ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models (2026-06-25) VLA
• hil-umi-human-in-the-loop-post-training-umi — HIL-UMI: Bringing Human-in-the-Loop Post-Training of VLA Models to Universal Manipulation Interface (2026-09-18) VLA
• lessons-learned-real-i-challenge-icra-2026 — How to Better Train VLAs: Lessons Learned From the REAL-I Challenge at ICRA 2026 (2026-09-13) VLA
• vlact-representation-centric-continued-pretraining — Beyond Data Scaling: Representation-Centric Continued Pre-training for VLA Models (VLAct) (2026-08-27) VLA
• rmuscle-robotic-muscle-memory-efficient-vla-inference — rMuscle: Robotic Muscle Memory for Efficient VLA Model Inference (2026-09-16) VLA
• vla-ulap-interleaving-cloud-vla-calls-edge — VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge (2026-09-16) VLA
• actionpiece-rethinking-action-tokenization-autoregressive-vla — ActionPiece: Rethinking Action Tokenization for Autoregressive VLA Models (2026-09-15) VLA
• fluxvla-engine-one-stop-vla-engineering-platform — FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence (2026-09-14) VLA
• towards-high-dof-dexterous-manipulation-vla-post-training — Towards High-DoF Dexterous Manipulation through VLA Post-Training (2026-09-17) VLA
• harbor-harness-framework-agentic-robot-rl — HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning (2026-06-07) RL-Robotics
• learning-more-from-less-rl-from-hindsight — Learning More from Less: Reinforcement Learning from Hindsight (LfH) (2026-07-10) RL-Robotics
• retvl-retry-supervised-value-learning-robot-imitation — Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation (ReTVL) (2026-07-06) RL-Robotics
• otql-optimal-transport-q-learning-flow-policy-steering — Optimal Transport Q-Learning for Flow Policy Steering and Acceleration (OTQL) (2026-07-07) RL-Robotics
• intrinsic-robot-rewarding-reusing-vla-representations — Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement (2026-09-15) RL-Robotics
• gr2po-group-relative-return-policy-optimization — GR2PO: Group Relative Return Policy Optimization for Continuous Robot Control (2026-09-16) RL-Robotics
• rl-real-time-vision-language-action-policies — Reinforcement Learning for Real-Time Vision-Language-Action Policies (2026-09-16) RL-Robotics
• learning-process-rewards-success-visitation-matching — Learning Process Rewards via Success Visitation Matching for Efficient RL (2026-06-26) RL-Robotics
• coherent-off-policy-improvement-large-behavior-models — Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards (2026-06-02) RL-Robotics
• helix-25-zero-shot-30-home-generalization — Helix 2.5: Zero-Shot 30-Home Generalization (2026-09-17) Humanoid
• apptronik-apollo-2-robot-park — Apptronik Unveils Apollo 2 and Opens “Robot Park” Data-Collection Facility (2026-06-30) Humanoid
• openhlm-empirical-recipe-whole-body-humanoid-loco-manipulation — OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation (2026-06-20) Humanoid
• omnicontact-chaining-meta-skills-contact-flow — OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation (2026-06-24) Humanoid
• pot-vla-persistent-3d-object-tokens-humanoid-vla — Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation (2026-07-20) Humanoid
• spot-spatial-perception-long-horizon-humanoid-teleoperation — SPOT: Spatial Perception-Oriented Long-Horizon Humanoid Teleoperation (2026-09-07) Humanoid
• viloman-visual-proprioceptive-whole-body-loco-manipulation — ViLoMan: Learning Visual-Proprioceptive Whole-Body Loco-Manipulation Skills for Humanoid Robots (2026-09-16) Humanoid
• glori-closed-loop-whole-body-tracking-humanoid — GLoRI: Closed-Loop Whole-Body Tracking with Global-Local Reference Interaction for Humanoid Loco-Manipulation (2026-09-05) Humanoid
• dextouch-wm-tactile-world-models-human-touch — DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation (2026-09-19) WorldModels
• ge-act-20-pretraining-scaling-world-action-model — GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation (2026-09-04) WorldModels
• wave-go-world-model-navigation-wheel-legged-robots — WAVE-Go: World-Model Navigation with Adaptive Execution for Wheel-Legged Robots (2026-09-15) WorldModels
• gigabrain-wbc-05-behavior-world-model-whole-body-control — GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction (2026-08-18) WorldModels
• feel-wm-world-models-off-road-navigation — Feeling Terrain Before Crossing: World Models for Off-Road Navigation (Feel-WM) (2026-09-16) WorldModels
• dido-distilling-interaction-centric-dynamics-one-step-denoising — DIDO: Distilling Interaction-Centric Dynamics into One-Step Denoising for World Action Models (2026-09-13) WorldModels
• modar-modality-autoregressive-world-action-models — Modality-Autoregressive World-Action Models (ModAR) (2026-09-15) WorldModels
• ewam-enhanced-world-action-model-closed-loop-online-adaptation — EWAM: An Enhanced World Action Model for Closed-Loop Online Adaptation in Embodied Intelligence (2026-06-12) WorldModels
• agentic-real2sim-physics-based-world-modeling-vl-agents — Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents (2026-07-19) WorldModels
• pointzero-3d-point-track-completion-transferable-3d-dynamics — PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics (2026-09-16) WorldModels
• wla3-world-latent-action-modeling-semantics-dynamics-kinematics — WLA³: World Latent Action Modeling for Semantics, Dynamics, and Kinematics (2026-09-13) WorldModels
• zing-05-playable-worlds-real-time-joint-action-text-control — Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control (2026-09-15) WorldModels
• wholebodywam-wbc-grounded-coordination-humanoid-loco-manipulation — WholeBodyWAM: Generalizing Pre-trained World-Action Priors to Humanoid Loco-Manipulation via WBC-Grounded Coordination (2026-09-15) WorldModels
• wholebodywam-scalable-motion-priors-unimotion-4k — WholeBodyWAM: Learning Whole-Body World Action Models with Scalable Motion Priors (2026-09-16) WorldModels
• robodrop-curating-vla-post-training-data-gradient-compatibility — RoboDrop: Curating VLA Post-Training Data via Local Gradient Compatibility (2026-09-27) VLA
• redflow-redirect-failure-action-level-corrections-flow-matching-vla — RedFlow: Redirect Failure into Action-Level Corrections for Flow-matching VLA Policy (2026-09-27) VLA
• in-context-robot-learning-vlm-agents — In-Context Robot Learning with VLM Agents (2026-09-27) VLA
• counteralign-counterfactual-supervision-vla — CounterAlign: Counterfactual Supervision for Vision-Language-Action Models (2026-09-27) VLA
• predvla-predictive-sensorimotor-modeling-sub-million-parameter — PredVLA: Predictive Sensorimotor Modeling for Sub-Million-Parameter Robot Manipulation (2026-09-27) VLA
• world-models-embodied-intelligence-plausible-controllable-actionable — World Models for Embodied Intelligence: From Plausible to Controllable to Actionable (2026-09-27) WorldModels
• world-action-models-robot-learning-control-survey — World-Action Models for Robot Learning and Control: A Survey (2026-09-27) WorldModels
• motus2-self-evolving-general-world-model-dexterous-manipulation — Motus2: A Self-Evolving General World Model for Dexterous Manipulation (2026-09-27) WorldModels
• learning-to-act-while-waiting-rl-finetuning-inference-latency — Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency (2026-09-27) RL-Robotics
• graft-grounded-efficient-online-reinforcement-adaptation-fine-grained-manipulation — GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot Manipulation (2026-09-27) RL-Robotics
• fierce-generalist-robot-policies-fast-specialists-progress-failure-feedback — FIERCE: From Generalist Robot Policies to Fast Specialists via Progress-Failure Feedback (2026-09-27) RL-Robotics
• bridge-open-source-humanoid-platform-morphology-control-co-design — BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI (2026-09-27) Humanoid
• swingbot-learning-whole-body-brachiation-humanoid-robots — SwingBot: Learning Whole-Body Brachiation for Humanoid Robots (2026-09-27) Humanoid
• dissecting-advantage-guided-post-training-vla-policies — Dissecting Advantage-Guided Post-Training for Vision-Language-Action Policies (2026-09-23) VLA
• self-adaptive-vla-robust-robot-deployment — Self-Adaptive VLA for Robust Robot Deployment (2026-09-24) VLA
• recastvla-past-interaction-future-control-adaptive-policy-states — RecastVLA: From Past Interaction to Future Control with Adaptive Policy States (2026-09-26) VLA
• phyvisgen-physically-visually-high-fidelity-robotic-manipulation-data-generation — PhyVisGen: Physically and Visually High-Fidelity Robotic Manipulation Data Generation (2026-09-22) VLA
• vlarl-augmenting-vla-simulation-trained-latent-conditioned-residual-rl — VLaRL: Augmenting Vision-Language-Action Models with Simulation-Trained Latent-Conditioned Residual RL (2026-09-25) VLA
• groundingpi-grounding-foundation-model-physical-intelligence-visual-primitives — GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives (2026-09-30) VLA
• worldline-action-driven-visual-simulation-robotic-manipulation — WorldLine: Action-Driven Visual Simulation for Robotic Manipulation (2026-09-29) WorldModels
• robocoach-world-models-active-coaches-compositional-robot-skills — RoboCoach: World Models as Active Coaches for Compositional Robot Skills (2026-09-30) WorldModels
• world-action-agent-harnessing-vlms-world-action-rehearsal — World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal (2026-09-24) WorldModels
• data-pyramid-embodied-manipulation-survey — Data Pyramid for Embodied Manipulation: A Survey (2026-07-27) WorldModels
• find-something-you-cant-do-agentic-rl-self-improving-vla — Find Something You Can’t Do: Agentic Real-World Reinforcement Learning for Self-Improving VLA Models (2026-09-25) RL-Robotics
• parts-real-world-subtask-rl-long-horizon-manipulation-minimal-human-intervention — From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention (2026-09-21) RL-Robotics
• res-hil-human-guided-residual-rl-sample-efficient-dexterous-manipulation — Res-HIL: Human-Guided Residual Reinforcement Learning for Sample-Efficient Dexterous Manipulation (2026-09-24) RL-Robotics
• tear-test-time-adaptation-manipulation-policies-actuator-degradation — Test-Time Adaptation of Manipulation Policies Under Actuator Degradation (2026-09-28) RL-Robotics
• scout-scouting-dynamics-gap-test-time-policy-adaptation — Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback (2026-09-28) RL-Robotics
• preferenceflow-test-time-guidance-flow-matching-robot-policies-human-interventions — PreferenceFlow: Test-Time Guidance of Flow-Matching Robot Policies from Human Interventions (2026-09-28) RL-Robotics
• prism-grpo-faster-vla-policy-optimization-splitting-same-outcome-groups — Prism-GRPO: Faster VLA Policy Optimization via Splitting Same-outcome Groups (2026-08-18) RL-Robotics
• dexweave-learning-dexterous-humanoid-loco-manipulation-human-demonstrations — DexWeave: Learning Dexterous Humanoid Loco-Manipulation from Human Demonstrations (2026-09-28) Humanoid
• prism-counterfactual-video-generation-scalable-humanoid-loco-manipulation — Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation (2026-09-30) Humanoid
• wb-wam-heterogeneous-body-hand-pretraining-humanoid-loco-manipulation — WB-WAM: Heterogeneous Body-Hand Pre-training for Humanoid Loco-Manipulation (2026-09-28) Humanoid
• tango-humanoid-navigation-cluttered-environments-whole-body-vla — TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model (2026-09-08) Humanoid
• learning-diverse-humanoid-tasks-synthetic-video-scenarios-without-real-world-data — Learning Diverse Humanoid Tasks via Synthetic Video Scenarios without Real World Data (2026-07-22) Humanoid
• skild-ai-physical-self-play — Skild AI: Physical Self-Play (2026-09-23) Humanoid
• ici-vla-in-context-imitation-spatiotemporally-aligned-demonstrations — ICI-VLA: In-Context Imitation with Spatiotemporally Aligned Demonstrations for Vision-Language-Action Models (2026-09-07) VLA
• infinova-infinite-novel-view-augmentation-viewpoint-invariant-robot-policies — InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies (2026-09-23) VLA
• turbovla-real-time-vla-32hz-rtx4090 — TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM (2026-07-29) VLA
• devol-one-autoregressive-mixture-transformers-vla-latent-world-modeling — Devol-ONE: One Autoregressive Mixture of Transformers to Unify Vision-Language-Action and Latent World Modeling (2026-09-26) VLA
• where-predictive-supervision-goes-shapes-what-vla-policies-learn — Where Predictive Supervision Goes Shapes What VLA Policies Learn (2026-09-29) VLA
• ati-vla-action-centric-predictive-vla-actionable-alignment-adaptive-injection — ATI-VLA: Action-Centric Predictive Vision-Language-Action Models via Actionable Alignment Then Adaptive Injection (2026-10-01) VLA
• fewer-tokens-better-action-gpt-6-astra-robot-agents — Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens (2026-10-01) VLA
• wbag-whole-body-attached-geometry-safety-framework-vla — WBAG: A Whole-Body and Attached-Geometry Safety Framework for Vision-Language-Action Manipulation (2026-10-01) VLA
• is-success-all-you-need-input-perturbations-vla-tabletop-manipulation — Is Success All You Need? Investigating the Impact of Input Perturbations on VLA Behaviour in Tabletop Manipulation Tasks (2026-10-01) VLA
• chunkvla-am-parallel-action-chunking-additive-manufacturing — ChunkVLA-AM: Parallel Action Chunking for Vision-Language-Action Robot Control in Additive Manufacturing (2026-10-01) VLA
• continuous-conditioning-vlas-emg-visual-task-descriptors — Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors (2026-10-01) VLA
• encoded-but-not-in-control-grounding-gap-vision-language-robot-policies — Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies (2026-10-05) VLA
• a-safe-action-is-not-enough-feasible-future-decoding-vla-policies — A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies (2026-10-04) VLA
• smart-zero-shot-sim-to-real-articulated-object-manipulation-synthetic-pretraining — SMART: Zero-Shot Sim-to-Real Articulated Object Manipulation via Large-Scale Synthetic Pretraining (2026-10-06) VLA
• vla-acl-action-consistent-visual-token-pruning — VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models (2026-10-06) VLA
• esp-energy-score-policy-one-step-multimodal-action-generation — ESP: Energy-Score Policy for One-Step Multimodal Action Generation (2026-10-06) VLA
• stairvla-stage-aware-hierarchical-action-generation — StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models (2026-10-06) VLA
• bigym-2-benchmarking-humanoid-household-manipulation — BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation (2026-10-06) VLA
• vidal-visual-dynamics-grounded-action-latent-space-vla — ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models (2026-10-06) VLA
• warefly-vla-uav-navigation-human-tracking-smart-warehouses — WareFly-VLA: A Vision-Language-Action Framework for UAV Navigation and Human Tracking in Smart Warehouses (2026-10-06) VLA
• acttune-action-aware-precision-gpu-adaptation-energy-efficient-vla-inference — ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference (2026-10-06) VLA
• mim-vla-physical-interaction-representations-gripper-motor-feedback — MIM-VLA: Learning Physical Interaction Representations from Gripper Motor Feedback (2026-10-06) VLA
• vommi-collecting-leveraging-portable-demonstrations-mobile-manipulation — VOMMI: Collecting and Leveraging Portable Demonstrations for Mobile Manipulation (2026-10-06) VLA
• adapting-vla-models-unknown-visual-disruptions-during-execution — Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution (2026-10-06) VLA
• commit-while-futures-agree-consequence-aware-adaptive-action-chunking — Commit While Futures Agree: Consequence-Aware Adaptive Action Chunking for Robot Manipulation (2026-10-06) VLA
• towards-efficient-robotic-manipulation-models-self-recursive-pruning — Towards Efficient Robotic Manipulation Models with Self-Recursive Pruning (2026-10-06) VLA
• dreamtrue-action-faithful-robot-world-model-counterfactual-post-training — DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training (2026-10-08) WorldModels
• vigar-rethinking-world-action-model-compositional-in-context-manipulation — Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation (ViGAR) (2026-10-01) WorldModels
• hwam-humanoid-world-action-model-joint-state-action-generation — HWAM: Humanoid World Action Model With Joint State-Action Generation (2026-10-08) WorldModels
• lac-wm-cross-embodiment-robot-foundation-world-models-latent-actions — Cross-Embodiment Robot Foundation World Models with Latent Actions (LAC-WM) (2026-10-07) WorldModels
• delta-wam-distilling-action-tangent-fields-world-action-models — ΔWAM: Distilling Action Tangent Fields into World Action Models (2026-10-07) WorldModels
• pewam-keep-the-effect-drop-the-actor-programmable-effect-to-execution-world-action-models — Keep the Effect, Drop the Actor: Programmable Effect-to-Execution World-Action Models (PEWAM) (2026-10-01) WorldModels
• wm-craftnet-world-synesthesia-model-dexterous-in-hand-manipulation — WM-Craftnet: World Synesthesia Model for Generalizable and Robust Dexterous In-Hand Manipulation (2026-09-08) WorldModels
• uniintervene-pp-adaptive-intervention-agent-real-world-rl — UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning (2026-10-04) RL-Robotics
• roboprompt-intuitive-robot-policy-steering-sparse-human-input — RoboPrompt: Intuitive Robot Policy Steering with Sparse Human Input (2026-10-07) RL-Robotics
• embodiedrsi-active-continual-robot-learning-hypothesis-guided-co-evolution — EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution (2026-10-07) RL-Robotics
• agentic-rsr-real-to-sim-to-real-scene-reconstruction-execution-grounded-robot-policies — Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies (2026-10-07) RL-Robotics
• hulk-learning-whole-body-forceful-loco-manipulation-humanoids — HULK: Learning Whole-Body Forceful Loco-Manipulation for Humanoids (2026-10-06) Humanoid
• intermimicgen-scaling-humanoid-loco-manipulation-self-evolving-motion-imitation — InterMimicGen: Scaling Humanoid Loco-Manipulation through Self-Evolving Motion Imitation (2026-10-05) Humanoid
• humanoid-horizon-extending-task-horizon-whole-body-loco-manipulation — Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward Gating (2026-10-06) Humanoid
• dataset-free-compliant-humanoid-loco-manipulation-dynamic-online-posture — Dataset-Free Compliant Humanoid Loco-Manipulation with Dynamic Online Posture (2026-10-05) Humanoid
• general-humanoid-loco-manipulation-egocentric-whole-body-human-data-pretraining — Towards a General Humanoid Loco-Manipulation Model via Egocentric Whole-Body Human Data Pretraining (2026-10-01) Humanoid
• humanoidtoolbench-benchmarking-humanoid-tool-use-selection-mobile-execution — HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution (2026-10-01) Humanoid
• mate-multi-agent-virtual-teleoperation-humanoid-collaboration-data-collection — MATE: Multi-Agent Virtual Teleoperation Platform for Humanoid Collaboration Data Collection (2026-09-22) Humanoid

---

Weekly Digests

• 2026-05-05-weekly-digest — Weekly Digest 2026-05-05 (10 new entries)
• 2026-05-06-weekly-digest — Weekly Digest 2026-05-06 (8 new entries)
• 2026-05-11-weekly-digest — Weekly Digest 2026-05-11 (8 new entries)
• 2026-05-18-weekly-digest — Weekly Digest 2026-05-18 (11 new entries)
• 2026-06-04-weekly-digest — Weekly Digest 2026-06-04 (11 new entries)
• 2026-06-08-weekly-digest — Weekly Digest 2026-06-08 (7 new entries)
• 2026-06-15-weekly-digest — Weekly Digest 2026-06-15 (11 new entries)
• 2026-06-22-weekly-digest — Weekly Digest 2026-06-22 (14 new entries)
• 2026-06-29-weekly-digest — Weekly Digest 2026-06-29 (13 new entries)
• 2026-07-06-weekly-digest — Weekly Digest 2026-07-06 (17 new entries)
• 2026-07-13-weekly-digest — Weekly Digest 2026-07-13 (12 new entries)
• 2026-07-20-weekly-digest — Weekly Digest 2026-07-20 (9 new entries)
• 2026-07-26-weekly-digest — Weekly Digest 2026-07-26 (22 new entries)
• 2026-08-02-weekly-digest — Weekly Digest 2026-08-02 (26 new entries)
• 2026-08-09-weekly-digest — Weekly Digest 2026-08-09 (36 new entries)
• 2026-08-16-weekly-digest — Weekly Digest 2026-08-16 (25 new entries)
• 2026-08-23-weekly-digest — Weekly Digest 2026-08-23 (29 new entries)
• 2026-08-30-weekly-digest — Weekly Digest 2026-08-30 (36 new entries)
• 2026-09-06-weekly-digest — Weekly Digest 2026-09-06 (22 new entries)
• 2026-09-13-weekly-digest — Weekly Digest 2026-09-13 (20 new entries)
• 2026-09-20-weekly-digest — Weekly Digest 2026-09-20 (49 new entries)
• 2026-09-27-weekly-digest — Weekly Digest 2026-09-27 (13 new entries)
• 2026-10-04-weekly-digest — Weekly Digest 2026-10-04 (23 new entries)
• 2026-10-11-weekly-digest — Weekly Digest 2026-10-11 (44 new entries)

---

Last updated: 2026-10-11