InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactionsby Pan Zhang, Xiaoyi…
TimeRefine: Temporal Grounding with Time Refining Video LLMby Xizi Wang, Feng Cheng, Ziyang Wang, Huiyu…
Olympus: A Universal Task Router for Computer Vision Tasksby Yuanze Lin, Yunsheng Li, Dongdong Chen,…
Bridging AI and Science: Implications from a Large-Scale Literature Analysis of AI4Scienceby Yutong Xie, Yijun…
Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Modelsby Fan Zhang, Shulin Tian,…
Systematic Analysis of LLM Contributions to Planning: Solver, Verifier, Heuristicby Haoming Li, Zhaoliang Chen, Songyuan…
From Noise to Nuance: Advances in Deep Generative Image Modelsby Benji Peng, Chia Xin Liang,…
On Round-Off Errors and Gaussian Blur in Superresolution and in Image Registrationby Serap A. SavariFirst…
Memory Layers at Scaleby Vincent-Pierre Berges, Barlas Oğuz, Daniel Haziza, Wen-tau Yih, Luke Zettlemoyer, Gargi…
AutoPatent: A Multi-Agent Framework for Automatic Patent Generationby Qiyao Wang, Shiwen Ni, Huaren Liu, Shule…