中文
相关论文

相关论文: McSc: Motion-Corrective Preference Alignment for V…

200 篇论文

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Hengjia Li , Liming Jiang , Qing Yan , Yizhi Song , Hao Kang , Zichuan Liu , Xin Lu , Boxi Wu , Deng Cai

Multi-modal Large Language Models (MLLMs) excel at single-image tasks but struggle with multi-image understanding due to cross-modal misalignment, leading to hallucinations (context omission, conflation, and misinterpretation). Existing…

计算机视觉与模式识别 · 计算机科学 2025-05-29 Xudong Li , Mengdan Zhang , Peixian Chen , Xiawu Zheng , Yan Zhang , Jingyuan Zheng , Yunhang Shen , Ke Li , Chaoyou Fu , Xing Sun , Rongrong Ji

Video-and-Language Inference is a recently proposed task for joint video-and-language understanding. This new task requires a model to draw inference on whether a natural language statement entails or contradicts a given video clip. In this…

计算机视觉与模式识别 · 计算机科学 2021-08-10 Juncheng Li , Siliang Tang , Linchao Zhu , Haochen Shi , Xuanwen Huang , Fei Wu , Yi Yang , Yueting Zhuang

Despite the promising progress of recent autoregressive models in text-to-image (T2I) generation, their ability to handle multi-attribute and ambiguous prompts remains limited. To address these limitations, existing works have applied…

计算机视觉与模式识别 · 计算机科学 2025-08-27 Yaqi Li , Peng Chen , Mingyang Han , Pi Bu , Haoxiang Shi , Runzhou Zhao , Yang Yao , Xuan Zhang , Jun Song , Bo Zheng

Affordance-centric Question-driven Task Completion (AQTC) for Egocentric Assistant introduces a groundbreaking scenario. In this scenario, through learning instructional videos, AI assistants provide users with step-by-step guidance on…

计算机视觉与模式识别 · 计算机科学 2023-06-27 Chao Zhang , Shiwei Wu , Sirui Zhao , Tong Xu , Enhong Chen

Video identity customization seeks to produce high-fidelity videos that maintain consistent identity and exhibit significant dynamics based on users' reference images. However, existing approaches face two key challenges: identity…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Hengjia Li , Lifan Jiang , Xi Xiao , Tianyang Wang , Hongwei Yi , Boxi Wu , Deng Cai

Generative models have demonstrated remarkable capability in synthesizing high-quality text, images, and videos. For video generation, contemporary text-to-video models exhibit impressive capabilities, crafting visually stunning videos.…

While generative video models have achieved remarkable fidelity and consistency, applying these capabilities to video editing remains a complex challenge. Recent research has explored motion controllability as a means to enhance…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Ryan Burgert , Charles Herrmann , Forrester Cole , Michael S Ryoo , Neal Wadhwa , Andrey Voynov , Nataniel Ruiz

Multimodal sentiment analysis aims to integrate textual, acoustic, and visual information for deep emotional understanding. Despite the progress of multimodal large language models (MLLMs) via supervised fine-tuning, their "black-box"…

计算与语言 · 计算机科学 2026-04-14 Miaosen Luo , Zhenhao Yang , Jieshen Long , Jinghu Sun , Yichu Liu , Sijie Mai

Reward-based fine-tuning of video diffusion models is an effective approach to improve the quality of generated videos, as it can fine-tune models without requiring real-world video datasets. However, it can sometimes be limited to specific…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Takehiro Aoshima , Yusuke Shinohara , Byeongseon Park

Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO) offers a lightweight, off-policy alternative to RL for…

计算与语言 · 计算机科学 2025-07-30 Anas Mohamed , Azal Ahmad Khan , Xinran Wang , Ahmad Faraz Khan , Shuwen Ge , Saman Bahzad Khan , Ayaan Ahmad , Ali Anwar

In computer animation, game design, and human-computer interaction, synthesizing human motion that aligns with user intent remains a significant challenge. Existing methods have notable limitations: textual approaches offer high-level…

计算机视觉与模式识别 · 计算机科学 2025-04-24 Yingjie Xi , Jian Jun Zhang , Xiaosong Yang

Recent advancements in human video generation and animation tasks, driven by diffusion models, have achieved significant progress. However, expressive and realistic human animation remains challenging due to the trade-off between motion…

计算机视觉与模式识别 · 计算机科学 2025-06-16 Chao Liang , Jianwen Jiang , Wang Liao , Jiaqi Yang , Zerong zheng , Weihong Zeng , Han Liang

Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts. However, extending these techniques to video generation remains challenging, with existing text-to-video…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Weifeng Chen , Yatai Ji , Jie Wu , Hefeng Wu , Pan Xie , Jiashi Li , Xin Xia , Xuefeng Xiao , Liang Lin

Video summarization intends to produce a concise video summary by effectively capturing and combining the most informative parts of the whole content. Existing approaches for video summarization regard the task as a frame-wise keyframe…

计算机视觉与模式识别 · 计算机科学 2023-05-31 Wujiang Xu , Runzhong Wang , Xiaobo Guo , Shaoshuai Li , Qiongxu Ma , Yunan Zhao , Sheng Guo , Zhenfeng Zhu , Junchi Yan

Text-to-image (T2I) generation has greatly enhanced creative expression, yet achieving preference-aligned generation in a real-time and training-free manner remains challenging. Previous methods often rely on static, pre-collected…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Yang Li , Songlin Yang , Xiaoxuan Han , Wei Wang , Jing Dong , Yueming Lyu , Ziyu Xue

Nowadays, training and evaluating DeepResearch-generated reports remain challenging due to the lack of verifiable reward signals. Accordingly, rubric-based evaluation has become a common practice. However, existing approaches either rely on…

Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Qunzhong Wang , Jie Liu , Jiajun Liang , Yilei Jiang , Yuanxing Zhang , Yaozhi Zheng , Xintao Wang , Pengfei Wan , Xiangyu Yue , Jiaheng Liu

Text-to-3D generation automates 3D content creation from textual descriptions, which offers transformative potential across various fields. However, existing methods often struggle to align generated content with human preferences, limiting…

计算与语言 · 计算机科学 2025-02-10 Zhenglin Zhou , Xiaobo Xia , Fan Ma , Hehe Fan , Yi Yang , Tat-Seng Chua

Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite these advancements, LVLMs often exhibit the hallucination…

机器学习 · 计算机科学 2024-11-05 Yiyang Zhou , Zhiyuan Fan , Dongjie Cheng , Sihan Yang , Zhaorun Chen , Chenhang Cui , Xiyao Wang , Yun Li , Linjun Zhang , Huaxiu Yao
‹ 上一页 1 8 9 10 下一页 ›