Kavli Affiliate: Long Zhang | First 5 Authors: Yun Wang, Yun Wang, , , | Summary: Video Large Language Models (Video-LLMs) excel at general video understanding but struggle with long-form videos due to context window limits. Consequently, recent approaches focus on keyframe retrieval, condensing lengthy videos into a small set of informative frames. Despite their […]

Kavli Affiliate: Yi Zhou | First 5 Authors: Kaiwen Huang, Kaiwen Huang, , , | Summary: Semi-supervised learning has gained considerable popularity in medical image segmentation tasks due to its capability to reduce reliance on expert-examined annotations. Several mean-teacher (MT) based semi-supervised methods utilize consistency regularization to effectively leverage valuable information from unlabeled data. However, […]

Kavli Affiliate: Long Zhang | First 5 Authors: Anxiang Zeng, Anxiang Zeng, , , | Summary: Recent R1-Zero-like research further demonstrates that reasoning extension has given large language models (LLMs) unprecedented reasoning capabilities, and Reinforcement Learning is the core technology to elicit its complex reasoning. However, conducting RL experiments directly on hyperscale models involves high […]

Kavli Affiliate: Zheng Zhu | First 5 Authors: Yuchu Jiang, Yuchu Jiang, , , | Summary: The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, that pose significant societal risks, including misinformation, inequity, security breaches, physical harm, and eroded public trust. […]

Kavli Affiliate: Zheng Zhu | First 5 Authors: Chaojun Ni, Chaojun Ni, , , | Summary: Reinforcement learning for training end-to-end autonomous driving models in closed-loop simulations is gaining growing attention. However, most simulation environments differ significantly from real-world conditions, creating a substantial simulation-to-reality (sim2real) gap. To bridge this gap, some approaches utilize scene reconstruction […]