Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models Paper • 2512.02044 • Published Nov 26 • 1
MMSearch-Plus: A Simple Yet Challenging Benchmark for Multimodal Browsing Agents Paper • 2508.21475 • Published Aug 29 • 2
GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning Paper • 2507.10628 • Published Jul 14 • 2