Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits Paper • 2512.20578 • Published Dec 23, 2025 • 83
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation Paper • 2512.24271 • Published 27 days ago • 62
Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization Paper • 2512.24615 • Published 26 days ago • 118
QuantiPhy: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models Paper • 2512.19526 • Published Dec 22, 2025 • 12
H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs Paper • 2512.01797 • Published Dec 1, 2025 • 2