中文
相关论文

相关论文: RealDPO: Real or Not Real, that is the Preference

200 篇论文

Video generation techniques have achieved remarkable advancements in visual quality, yet faithfully reproducing real-world physics remains elusive. Preference-based model post-training may improve physical consistency, but requires costly…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Wenxu Qian , Chaoyue Wang , Hou Peng , Zhiyu Tan , Hao Li , Anxiang Zeng

Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Zitong Huang , Kaidong Zhang , Yukang Ding , Chao Gao , Rui Ding , Ying Chen , Wangmeng Zuo

Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability…

计算机视觉与模式识别 · 计算机科学 2024-05-08 Massimiliano Pappa , Luca Collorone , Giovanni Ficarra , Indro Spinelli , Fabio Galasso

Human image generation is a key focus in image synthesis due to its broad applications, but even slight inaccuracies in anatomy, pose, or details can compromise realism. To address these challenges, we explore Direct Preference Optimization…

计算机视觉与模式识别 · 计算机科学 2025-04-10 Sanghyeon Na , Yonggyu Kim , Hyunjoon Lee

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

Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from…

计算机视觉与模式识别 · 计算机科学 2025-10-13 Ziyi Wu , Anil Kag , Ivan Skorokhodov , Willi Menapace , Ashkan Mirzaei , Igor Gilitschenski , Sergey Tulyakov , Aliaksandr Siarohin

Recent studies have identified Direct Preference Optimization (DPO) as an efficient and reward-free approach to improving video generation quality. However, existing methods largely follow image-domain paradigms and are mainly developed on…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Jie Du , Xinyu Gong , Qingshan Tan , Wen Li , Yangming Cheng , Weitao Wang , Chenlu Zhan , Suhui Wu , Hao Zhang , Jun Zhang

Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user…

计算机视觉与模式识别 · 计算机科学 2024-12-19 Runtao Liu , Haoyu Wu , Zheng Ziqiang , Chen Wei , Yingqing He , Renjie Pi , Qifeng Chen

Text-to-motion generation is essential for advancing the creative industry but often presents challenges in producing consistent, realistic motions. To address this, we focus on fine-tuning text-to-motion models to consistently favor…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Xiaofeng Tan , Hongsong Wang , Xin Geng , Pan Zhou

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…

计算与语言 · 计算机科学 2024-02-14 Víctor Gallego

With the rapid development of AIGC technology, significant progress has been made in diffusion model-based technologies for text-to-image (T2I) and text-to-video (T2V). In recent years, a few studies have introduced the strategy of Direct…

计算机视觉与模式识别 · 计算机科学 2025-02-05 Lifan Jiang , Boxi Wu , Jiahui Zhang , Xiaotong Guan , Shuang Chen

Direct Preference Optimization (DPO) helps reduce hallucinations in Video Multimodal Large Language Models (VLLMs), but its reliance on offline preference data limits adaptability and fails to capture true video-response misalignment. We…

计算机视觉与模式识别 · 计算机科学 2025-04-16 Xinpeng Ding , Kui Zhang , Jianhua Han , Lanqing Hong , Hang Xu , Xiaomeng Li

Direct Preference Optimization (DPO), which aligns models with human preferences through win/lose data pairs, has achieved remarkable success in language and image generation. However, applying DPO to video diffusion models faces critical…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Haoran Cheng , Qide Dong , Liang Peng , Zhizhou Sha , Weiguo Feng , Jinghui Xie , Zhao Song , Shilei Wen , Xiaofei He , Boxi Wu

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

Fine-grained video captioning aims to generate detailed, temporally coherent descriptions of video content. However, existing methods struggle to capture subtle video dynamics and rich detailed information. In this paper, we leverage…

人工智能 · 计算机科学 2026-03-24 Jisheng Dang , Yizhou Zhang , Hao Ye , Teng Wang , Siming Chen , Huicheng Zheng , Yulan Guo , Jianhuang Lai , Bin Hu

Recent advancements in video-audio joint generation have achieved remarkable success in semantic correspondence. However, achieving precise temporal synchronization, which requires fine-grained alignment between audio events and their…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Xin Cheng , Xihua Wang , Ying Ba , Yuyue Wang , Kaisi Guan , Yinbo Wang , Wenpu Li , Ruihua Song

The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answering, mathematical reasoning, and code generation. However,…

机器学习 · 计算机科学 2026-05-18 Xiaoqiang Lin , Arun Verma , Zhongxiang Dai , Daniela Rus , See-Kiong Ng , Bryan Kian Hsiang Low

Recent advancements in video generation have enabled the creation of high-quality, visually compelling videos. However, generating videos that adhere to the laws of physics remains a critical challenge for applications requiring realism and…

计算机视觉与模式识别 · 计算机科学 2025-08-15 Harold Haodong Chen , Haojian Huang , Qifeng Chen , Harry Yang , Ser-Nam Lim

In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role in this area. It works by using pairs of preferences…

计算与语言 · 计算机科学 2024-05-29 Yueqin Yin , Zhendong Wang , Yi Gu , Hai Huang , Weizhu Chen , Mingyuan Zhou

Recent advances in diffusion models have improved Real-World Image Super-Resolution (Real-ISR), but existing methods lack human feedback integration, risking misalignment with human preference and may leading to artifacts, hallucinations…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Miaomiao Cai , Simiao Li , Wei Li , Xudong Huang , Hanting Chen , Jie Hu , Yunhe Wang
‹ 上一页 1 2 3 10 下一页 ›