Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing
Paper • 2609.37334 • Published • 46
xrn
xxrrnn
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing upvoted a paper 8 days ago
GRACE: Generation-aware latent compression for efficient video generation upvoted a paper 8 days ago
Long-WAM: Scaling the Context of World-Action ModelsOrganizations
None yet
upvoted 4
papers 8 days ago
GRACE: Generation-aware latent compression for efficient video generation
Paper • 2610.10524 • Published • 89
Long-WAM: Scaling the Context of World-Action Models
Paper • 2610.10528 • Published • 111
TokenRouter: Efficient Serving System for Token-Level LLM Routing
Paper • 2610.12242 • Published • 143
upvoted 5
papers 13 days ago
FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
Paper • 2609.38585 • Published • 9
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling
Paper • 2609.38104 • Published • 10
AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines
Paper • 2610.01108 • Published • 14
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
Paper • 2609.37362 • Published • 19
Decoding Looped Transformers Better for (Almost) Free
Paper • 2610.02185 • Published • 46
upvoted 4
papers 15 days ago
SeLMRoute: Probabilistic Semantic Evidence for Large Language Model Routing
Paper • 2609.34736 • Published • 12
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends
Paper • 2609.39661 • Published • 13
LoopVL: Recurrent Visual Intelligence
Paper • 2609.38426 • Published • 485
Improving Test-Time Scaling with Adaptive Looped Transformers
Paper • 2609.35748 • Published • 61
upvoted 2
papers 17 days ago
updated 4
collections about 1 month ago