SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
Paper • 2611.02501 • Published • 15
xrn
xxrrnn
AI & ML interests
None yet
Recent Activity
upvoted a paper about 11 hours ago
SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding upvoted a paper about 11 hours ago
Wave Forcing: Towards Speed-of-Light Streaming Video Generation upvoted a paper 26 days ago
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress TestingOrganizations
None yet
upvoted 2
papers about 11 hours ago
upvoted 4
papers 26 days ago
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing
Paper • 2609.37334 • Published • 35
GRACE: Generation-aware latent compression for efficient video generation
Paper • 2610.10524 • Published • 65
Long-WAM: Scaling the Context of World-Action Models
Paper • 2610.10528 • Published • 93
TokenRouter: Efficient Serving System for Token-Level LLM Routing
Paper • 2610.12242 • Published • 119
upvoted 11
papers about 1 month ago
FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing
Paper • 2609.38585 • Published • 7
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling
Paper • 2609.38104 • Published • 8
AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines
Paper • 2610.01108 • Published • 12
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
Paper • 2609.37362 • Published • 10
Decoding Looped Transformers Better for (Almost) Free
Paper • 2610.02185 • Published • 25
SeLMRoute: Probabilistic Semantic Evidence for Large Language Model Routing
Paper • 2609.34736 • Published • 10
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends
Paper • 2609.39661 • Published • 12
LoopVL: Recurrent Visual Intelligence
Paper • 2609.38426 • Published • 41
Improving Test-Time Scaling with Adaptive Looped Transformers
Paper • 2609.35748 • Published • 62
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Paper • 2609.34981 • Published • 80
Disaggregated Quantization: Specializing LLM Prefill and Decode
Paper • 2609.26333 • Published • 84