Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published 4 days ago • 128
UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents Paper • 2505.21496 • Published 10 days ago • 38
Absolute Zero: Reinforced Self-play Reasoning with Zero Data Paper • 2505.03335 • Published May 6 • 168
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? Paper • 2504.13837 • Published Apr 18 • 127
4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models Paper • 2503.10437 • Published Mar 13 • 32
ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation Paper • 2502.18364 • Published Feb 25 • 36
ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation Paper • 2502.18364 • Published Feb 25 • 36