From the 1 of 12 linked papers with an AI index.
12 papers
UniVR: Thinking in Visual Space for Unified Visual Reasoning
Zhongwei Ren, Yunchao Wei, Yao Zhao +5
The paper presents UniVR, a system that learns complex visual reasoning, fine-grained physical dynamics, and long-term planning directly from raw video demonstrations using a novel…
SAMTok: Representing Any Mask with Two Words
Yikang Zhou, Tao Zhang, Dengxian Gong +13
Pixel-wise capabilities are essential for building interactive intelligent systems. However, pixel-wise multi-modal LLMs (MLLMs) remain difficult to scale due to complex region-lev…
Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
Jiahao Meng, Xiangtai Li, Haochen Wang +8
Most video reasoning models only generate textual reasoning traces without indicating when and where key evidence appears. Recent models such as OpenAI-o3 have sparked wide interes…
Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs
Haochen Wang, Yuhao Wang, Tao Zhang +13
While Multimodal Large Language Models (MLLMs) excel at holistic understanding, they struggle in capturing the dense world with complex scenes, requiring fine-grained analysis of i…
Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology
Haochen Wang, Xiangtai Li, Zilong Huang +9
Models like OpenAI-o3 pioneer visual grounded reasoning by dynamically referencing visual regions, just like human "thinking with images". However, no benchmark exists to evaluate…
PairUni: Pairwise Training for Unified Multimodal Language Models
Jiani Zheng, Zhiyang Teng, Kunpeng Qiu +6
Unified Vision-Language Models (UVLMs) perform both understanding and generation within a single architecture. Since these models rely on heterogeneous data and supervision, balanc…