FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing Paper • 2609.38585 • Published 8 days ago • 8
Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling Paper • 2609.38104 • Published 8 days ago • 9
AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines Paper • 2610.01108 • Published 6 days ago • 13
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing Paper • 2609.37362 • Published 8 days ago • 17
SeLMRoute: Probabilistic Semantic Evidence for Large Language Model Routing Paper • 2609.34736 • Published 9 days ago • 11
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends Paper • 2609.39661 • Published 7 days ago • 12
Improving Test-Time Scaling with Adaptive Looped Transformers Paper • 2609.35748 • Published 9 days ago • 59
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling Paper • 2609.34981 • Published 8 days ago • 136
Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published 15 days ago • 93