VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Paper • 2602.10693 • Published Feb 11 • 220
Flash-KMeans: Fast and Memory-Efficient Exact K-Means Paper • 2603.09229 • Published 24 days ago • 82
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use Paper • 2603.11076 • Published 23 days ago • 5
LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning Paper • 2603.21065 • Published 12 days ago • 77
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? Paper • 2603.24472 • Published 9 days ago • 47
The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus Paper • 2603.20105 • Published 14 days ago • 36
TAPS: Task Aware Proposal Distributions for Speculative Sampling Paper • 2603.27027 • Published 6 days ago • 137
DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing Paper • 2603.28713 • Published 3 days ago • 15
Embarrassingly Simple Self-Distillation Improves Code Generation Paper • 2604.01193 • Published 1 day ago • 11