Folder: papers/vla

Jun 25, 2026

• vla
• language-action-pretraining
• language-grounding
• data-efficient
• pretraining

Jun 18, 2026

• efficiency
• model-compression
• layer-pruning
• fine-tuning
• training-free

Jun 16, 2026

• chain-of-thought
• long-horizon
• visual-prediction
• mixture-of-transformers
• subgoal-reasoning

Jun 15, 2026

• vla
• 3d-geometry
• geometric-foundation-model
• world-model
• robot-policy
• kaist
• eth-zurich

Jun 11, 2026

• lab-automation
• scientific-robotics
• protocol-execution
• Qwen3-VL
• DiT-action

Jun 09, 2026

• hierarchical-VLA
• hi-VLA
• options-framework
• task-decomposition
• VLM-planner
• Google-DeepMind
• systematic-study

Jun 08, 2026

• temporal-modeling
• memory
• imagination
• working-memory
• episodic-memory
• long-horizon
• VLA

Jun 05, 2026

• affordance
• intermediate-representation
• mixture-of-experts
• spatial-grounding
• data-augmentation
• VLA

Jun 04, 2026

• 3D-spatial-reasoning
• latent-priors
• co-training
• geometry
• VLA
• spatial-grounding

Jun 04, 2026

• vla
• world-models
• position-paper
• data-interfaces
• embodiment-gap
• reward-modeling
• survey

Jun 04, 2026

• vla
• speed-control
• trajectory-augmentation
• manipulation
• execution-speed

Jun 01, 2026

• dynamic-objects
• world-model
• latent-prediction
• optical-flow
• motion-compensation
• CMU
• AHEAD

Jun 01, 2026

• demo-conditioned
• cross-embodiment
• latent-planning
• end-effector-trace
• RoboCasa
• human-to-robot

May 29, 2026

• vla
• unified-model
• cross-embodiment
• navigation
• manipulation
• alibaba
• qwen

May 21, 2026

• online-adaptation
• curriculum-learning
• reward-synthesis
• test-time-RL
• agentic

May 18, 2026

• bimanual
• dexterous-manipulation
• open-source
• teleoperation
• dual-arm
• ICRA

May 18, 2026

• survey
• human-video
• data-efficient
• scalable-training
• latent-action
• IJCAI

May 13, 2026

• latent-action
• flow-matching
• pretraining
• MetaWorld
• LIBERO

May 11, 2026

• long-horizon
• subgoal-generation
• hierarchical
• embodied-reasoning
• compounding-errors

May 06, 2026

• latent-action
• pretraining
• cross-embodiment
• image-based
• action-based

May 01, 2026

• memory
• hierarchical
• hyperbolic-space
• long-horizon
• LIBERO
• experience-consolidation

Apr 24, 2026

• survey
• datasets
• benchmarks
• data-engines
• embodied-AI
• data-infrastructure

Apr 16, 2026

• compositional-generalization
• steerable
• multi-task
• cross-embodiment
• flow-matching
• physical-intelligence

Apr 15, 2026

• embodied-reasoning
• spatial-understanding
• industrial-robotics
• DeepMind
• Google
• Boston-Dynamics

Apr 09, 2026

• humanoid
• whole-body
• mixture-of-experts
• cross-embodiment
• loco-manipulation
• history-tokens

Apr 05, 2026

• machine-unlearning
• safety
• OpenVLA
• embodied-AI
• benchmark

Mar 29, 2026

• diffusion-policy
• progress-estimation
• world-model
• inverse-dynamics
• Microsoft-Research
• task-termination

Mar 27, 2026

• pretraining
• forward-dynamics
• inverse-dynamics
• action-free-video
• ICLR-2026

Mar 23, 2026

• chain-of-thought
• parallel-reasoning
• spatial-understanding
• task-planning
• LIBERO
• RoboCasa
• HKUST

Mar 22, 2026

• RL-alignment
• test-time-reasoning
• language-action
• LIBERO
• CALVIN
• reinforcement-learning

Mar 16, 2026

• humanoid
• cross-embodiment
• open-source
• foundation-model
• EgoScale

Mar 10, 2026

• subtask-aware
• post-training
• world-model
• offline-RL
• long-horizon
• instruction-grounding

Feb 27, 2026

• chain-of-thought
• multimodal-reasoning
• visual-subgoal
• mixture-of-transformers
• ICML-2026
• long-horizon

Feb 11, 2026

• foundation-model
• cross-embodiment
• action-manifold
• dataset
• Alibaba
• multi-robot
• diffusion

Jan 16, 2026

• chain-of-thought
• action-reasoning
• CVPR-2026
• manipulation
• explicit-reasoning
• diffusion