Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better Paper • 2506.09040 • Published Jun 10 • 34
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2 • 185
MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI Paper • 2311.16502 • Published Nov 27, 2023 • 37
