Ruozhen He, Meng Wei, Ziyan Yang, Vicente Ordonez
Multi-shot video generation extends single-shot generation to coherent visual narratives, yet maintaining consistent characters, objects, and locations across shots remains a challenge over long sequences. Existing…
cs.CVcs.AI
Ziyu Guo, Rain Liu, Xinyan Chen, Pheng-Ann Heng
Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is to directly generate images via unified models during reasoning, but…
cs.CVcs.AIcs.CL
Kaixin Zhu, Yiwen Tang, Yifan Yang, Renrui Zhang, Bohan Zeng, Ziyu Guo, Ruichuan An, Zhou Liu, Qizhi Chen, Delin Qu, Jaehong Yoon, Wentao Zhang
High-quality 3D scene reconstruction has recently advanced toward generalizable feed-forward architectures, enabling the generation of complex environments in a single forward pass. However, despite their strong…
cs.CVcs.AI
Jiaxin Wu, Yihao Pi, Yinling Zhang, Yuheng Li, Xueyan Zou
Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and motion remains challenging. Most existing video evaluation pipelines…
cs.CVcs.AI
Ellwil Sharma, Arastu Sharma
Scaling Scientific Machine Learning (SciML) toward universal foundation models is bottlenecked by negative transfer: the simultaneous co-training of disparate partial differential equation (PDE) regimes can induce…
cs.LGcs.AIphysics.comp-ph
Shang Zhou, Wenhao Chai, Kaiyuan Liu, Huanzhi Mao, Qiuyang Mang, Jingbo Shang
Test-time compute scaling is a primary axis for improving LLM reasoning. Existing methods primarily scale depth by extending a single reasoning trace. Scaling breadth by sampling multiple candidates in parallel is…
cs.AI
Chenyu Lian, Hong-Yu Zhou, Jing Qin
Disease screening is critical for early detection and timely intervention in clinical practice. However, most current screening models for medical images suffer from limited interpretability and suboptimal performance.…
cs.CVcs.AIcs.LG
Pratinav Seth, Vinay Kumar Sankarapu
This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI governance frameworks enacted between 2019 and early 2026 require…
cs.LGcs.AI
Xiang Fan, Yuheng Wang, Bohan Fang, Zhongzheng Ren, Ranjay Krishna
Video generation powers a vast array of downstream applications. However, while the de facto standard, i.e., latent diffusion models, typically employ heavily conditioned denoising networks, their decoders often remain…
cs.CVcs.LG
ML Nissen Gonzalez, Melwina Albuquerque, Laurence Wroe, Jacob Meyer Cohen, Logan Riggs Smith, Thomas Dooms
Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite. Existing similarity measures evaluate either empirical behaviour,…
cs.LG
Zhuohang Li, Liqun Huang, Wei Xu, Zhengming Zhu, Nie Lin, Xiao Ma, Xinjun Sheng, Ruoshi Wen
Vision-Language-Action (VLA) models are prone to compounding errors in dexterous manipulation, where high-dimensional action spaces and contact-rich dynamics amplify small policy deviations over long horizons. While…
cs.ROcs.LG
Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong, Arun Verma, Alok Prakash, Nancy F. Chen, Bryan Kian Hsiang Low, Daniela Rus, Armando Solar-Lezama
Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require timely, domain-specific…
cs.CLcs.AIcs.LG
Zhengxi Lu, Zhiyuan Yao, Zhuowen Han, Zi-Han Wang, Jinyang Wu, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy…
cs.LGcs.AIcs.CL