Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 27 days ago • 323
Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs Paper • 2604.05643 • Published 28 days ago • 13
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published Apr 3 • 626
UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems Paper • 2604.00590 • Published Apr 1 • 8
TAPS: Task Aware Proposal Distributions for Speculative Sampling Paper • 2603.27027 • Published Mar 27 • 143