JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence Paper • 2510.23538 • Published Oct 27 • 96
Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration Paper • 2508.13755 • Published Aug 19 • 14
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR Paper • 2508.14029 • Published Aug 19 • 118
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning Paper • 2506.07044 • Published Jun 8 • 113
FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving Paper • 2502.20238 • Published Feb 27 • 23