Paper Archive

Muhammad Maaz, Hanoona Rasheed, Fahad Shahbaz Khan, Salman Khan 11/28/2025 arxiv

Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while being logically inconsistent or weakly grounded in visual ev...

Hanoona Rasheed, Mohammed Zumri, Muhammad Maaz, Ming-Hsuan Yang, Fahad Shahbaz Khan, Salman Khan 11/28/2025 arxiv

Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still "think about videos" ie once a video is encoded, reasoning unfolds entirely in text, treating visual input as a static context. This passive paradigm creates a semantic bottleneck: models cannot rewatch...

Zhizhou Zhong, Yicheng Ji, Zhe Kong, Yiying Liu, Jiarui Wang, Jiasun Feng, Lupeng Liu, Xiangyi Wang, Yanjia Li, Yuqing She, Ying Qin, Huan Li, Shuiyang Mao, Wei Liu, Wenhan Luo 11/28/2025 arxiv

Recently, multi-person video generation has started to gain prominence. While a few preliminary works have explored audio-driven multi-person talking video generation, they often face challenges due to the high costs of diverse multi-person data collection and the difficulty of driving multiple iden...

Yiping Wang, Shao-Rong Su, Zhiyuan Zeng, Eva Xu, Liliang Ren, Xinyu Yang, Zeyi Huang, Xuehai He, Luyao Ma, Baolin Peng, Hao Cheng, Pengcheng He, Weizhu Chen, Shuohang Wang, Simon Shaolei Du, Yelong Shen 11/28/2025 arxiv

Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to improve bounds on open problems. However, it relies on ensembles of frontier LLMs to achieve new bounds and is a pure infe...

Jiahao Guo, Sinan Du, Jingfeng Yao, Wenyu Liu, Bo Li, Haoxiang Cao, Kun Gai, Chun Yuan, Kai Wu, Xinggang Wang 11/28/2025 arxiv

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations, optimized for multimodal understanding tasks, harbor an inhere...

Hans Gundlach, Jayson Lynch, Matthias Mertens, Neil Thompson 11/28/2025 arxiv

Language models have seen enormous progress on advanced benchmarks in recent years, but much of this progress has only been possible by using more costly models. Benchmarks may therefore present a warped picture of progress in practical capabilities per dollar. To remedy this, we use data from Artif...

Tianlong Huang, Zhiyuan Li 11/28/2025 arxiv

This paper studies the role of activation functions in learning modular addition with two-layer neural networks. We first establish a sharp expressivity gap: sine MLPs admit width-$2$ exact realizations for any fixed length $m$ and, with bias, width-$2$ exact realizations uniformly over all lengths....

Hang Yu, Di Zhang, Qiwei Du, Yanping Zhao, Hai Zhang, Guang Chen, Eduardo E. Veas, Junqiao Zhao 11/28/2025 arxiv

Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented trajectories present challenges for reward propagation, resulting in inaccurate value estimation and degraded policy performance. While tra...

Bernhard Klein, Falk Selker, Hendrik Borras, Sophie Steger, Franz Pernkopf, Holger Fröning 11/28/2025 arxiv

Machine learning models perform well across domains such as diagnostics, weather forecasting, NLP, and autonomous driving, but their limited uncertainty handling restricts use in safety-critical settings. Traditional neural networks often fail to detect out-of-domain (OOD) data and may output confid...

Junshu Tang, Jiacheng Liu, Jiaqi Li, Longhuang Wu, Haoyu Yang, Penghao Zhao, Siruis Gong, Xiang Yuan, Shuai Shao, Qinglin Lu 11/28/2025 arxiv

Recent advances in generative world models have enabled remarkable progress in creating open-ended game environments, evolving from static scene synthesis toward dynamic, interactive simulation. However, current approaches remain limited by rigid action schemas and high annotation costs, restricting...