English
Related papers

Related papers: Hierarchical Fine-grained Preference Optimization …

200 papers

Recent advancements in video generation have significantly improved the ability to synthesize videos from text instructions. However, existing models still struggle with key challenges such as instruction misalignment, content…

Computer Vision and Pattern Recognition · Computer Science 2025-02-10 Haibo Tong , Zhaoyang Wang , Zhaorun Chen , Haonian Ji , Shi Qiu , Siwei Han , Kexin Geng , Zhongkai Xue , Yiyang Zhou , Peng Xia , Mingyu Ding , Rafael Rafailov , Chelsea Finn , Huaxiu Yao

Recent progress in text-conditioned human motion generation has been largely driven by diffusion models trained on large-scale human motion data. Building on this progress, recent methods attempt to transfer such models for character…

Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consistency, exhibiting physically implausible dynamics over time.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Haoran Lu , Shang Wu , Jianshu Zhang , Maojiang Su , Guo Ye , Chenwei Xu , Lie Lu , Pranav Maneriker , Fan Du , Manling Li , Zhaoran Wang , Han Liu

Recent diffusion-based video generation models can synthesize visually plausible videos, yet they often struggle to satisfy physical constraints. A key reason is that most existing approaches remain single-stage: they entangle high-level…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Yibo Zhao , Hengjia Li , Xiaofei He , Boxi Wu

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Xiaoxuan He , Siming Fu , Zeyue Xue , Weijie Wang , Ruizhe He , Yuming Li , Dacheng Yin , Shuai Dong , Haoyang Huang , Hongfa Wang , Nan Duan , Bohan Zhuang

Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion naturalness, lip-sync…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 MengChao Wang , Qiang Wang , Fan Jiang , Mu Xu

We present LongVPO, a novel two-stage Direct Preference Optimization framework that enables short-context vision-language models to robustly understand ultra-long videos without any long-video annotations. In Stage 1, we synthesize…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Zhenpeng Huang , Jiaqi Li , Zihan Jia , Xinhao Li , Desen Meng , Lingxue Song , Xi Chen , Liang Li , Limin Wang

Videos can often be created by first outlining a global description of the scene and then adding local details. Inspired by this we propose a hierarchical model for video generation which follows a coarse to fine approach. First our model…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Lluis Castrejon , Nicolas Ballas , Aaron Courville

Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimensions remains a persistent challenge. Though reinforcement…

Large-scale text-to-image foundation models have achieved remarkable visual realism, yet generating human images with correct anatomical structures remains challenging. Existing approaches enforce anatomical constraints through…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Bao Li , Yuliang Xiu , Zhen Liu

Video diffusion models (VDMs) have demonstrated remarkable capabilities in text-to-video (T2V) generation. Despite their success, VDMs still suffer from degraded image quality and flickering artifacts. To address these issues, some…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Jiacheng Zhang , Jie Wu , Weifeng Chen , Yatai Ji , Xuefeng Xiao , Weilin Huang , Kai Han

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

Machine Learning · Computer Science 2026-01-13 Hanyang Zhao , Haoxian Chen , Yucheng Guo , Genta Indra Winata , Tingting Ou , Ziyu Huang , David D. Yao , Wenpin Tang

While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference datasets contain conflicting preference patterns, where…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Ming Li , Jie Wu , Justin Cui , Xiaojie Li , Rui Wang , Chen Chen

Anime video generation faces significant challenges due to the scarcity of anime data and unusual motion patterns, leading to issues such as motion distortion and flickering artifacts, which result in misalignment with human preferences.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Bingwen Zhu , Yudong Jiang , Baohan Xu , Siqian Yang , Mingyu Yin , Yidi Wu , Huyang Sun , Zuxuan Wu

Dexterous robotic hands often struggle to generalize effectively in complex environments due to the limitations of models trained on low-diversity data. However, the real world presents an inherently unbounded range of scenarios, making it…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Yufei Zhu , Yiming Zhong , Zemin Yang , Peishan Cong , Jingyi Yu , Xinge Zhu , Yuexin Ma

World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising basis for such simulators because they can generate diverse…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Pu Zhao , Juyi Lin , Timothy Rupprecht , Arash Akbari , Chence Yang , Rahul Chowdhury , Elaheh Motamedi , Arman Akbari , Yumei He , Chen Wang , Geng Yuan , Weiwei Chen , Yanzhi Wang

Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is hierarchical and fine-grained. To address this, we first…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Chenye Meng , Zejian Li , Zhongni Liu , Yize Li , Changle Xie , Kaixin Jia , Ling Yang , Huanghuang Deng , Shiying Ding , Shengyuan Zhang , Jiayi Li , Lingyun Sun

Most Video Large Language Models (Video-LLMs) adopt preference alignment techniques, e.g., DPO~\citep{rafailov2024dpo}, to optimize the reward margin between a winning response ($y_w$) and a losing response ($y_l$). However, the likelihood…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Xiaodong Wang , Jinfa Huang , Li Yuan , Peixi Peng

Recent advances in video generation models demonstrate their potential as world simulators, but they often struggle with videos deviating from physical laws, a key concern overlooked by most text-to-video benchmarks. We introduce a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Yongfan Chen , Xiuwen Zhu , Tianyu Li

Direct preference optimization (DPO) has shown success in aligning diffusion models with human preference. Previous approaches typically assume a consistent preference label between final generations and noisy samples at intermediate steps,…

Machine Learning · Computer Science 2025-02-05 Jie Ren , Yuhang Zhang , Dongrui Liu , Xiaopeng Zhang , Qi Tian