Tag: efficiency

Aug 04, 2026

• world-models
• latent-world-model
• efficiency
• robotwin

Jul 02, 2026

• deployment
• inference
• edge
• heterogeneous-hardware
• c-plus-plus
• runtime
• efficiency

Jun 27, 2026

• vla
• model-compression
• architecture
• redundancy
• language-backbone
• efficiency

Jun 26, 2026

• efficiency
• inference-speed
• rl-post-training
• action-chunking
• pruning

Jun 19, 2026

• world-model
• wam
• image-editing
• efficiency
• token-reduction
• inference-latency
• ablation

Jun 18, 2026

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

Jun 18, 2026

• persistent-memory
• non-markovian
• long-horizon
• gist-tokens
• anchor-frames
• efficiency

Jun 11, 2026

• world-model
• wam
• efficiency
• inference-speed
• token-sparse
• wan-2-2
• real-time-deployment

Jun 08, 2026

• world-models
• adaptive-reasoning
• efficiency
• multimodal

May 16, 2026

• vla
• distillation
• efficiency
• vla-posttraining

May 09, 2026

• VLA
• efficiency
• recurrent-transformer
• test-time-compute
• inference-optimization
• action-chunking

May 08, 2026

• visual-tokenization
• flow-matching
• adaptive-attention-pooling
• efficiency
• VLA

Feb 02, 2026

• disentangled
• dynamics
• efficiency
• MPC
• manipulation
• navigation
• foreground-background
• CVPR-2026