Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 48
Reasoning
-
-
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
Paper • 2505.23359 • Published • 38 -
OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation
Paper • 2506.02397 • Published • 36 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 146 -
How much do language models memorize?
Paper • 2505.24832 • Published • 4 -
GRIT: Teaching MLLMs to Think with Images
Paper • 2505.15879 • Published • 13 -
Reward Reasoning Model
Paper • 2505.14674 • Published • 37 -
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Paper • 2507.13348 • Published • 79 -
Why Language Models Hallucinate
Paper • 2509.04664 • Published • 199 -
Visual Diffusion Models are Geometric Solvers
Paper • 2510.21697 • Published • 20 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 512