English
Related papers

Related papers: Aligning Anime Video Generation with Human Feedbac…

200 papers

Aligning human preference and value is an important requirement for building contemporary foundation models and embodied AI. However, popular approaches such as reinforcement learning with human feedback (RLHF) break down the task into…

Artificial Intelligence · Computer Science 2024-12-03 Chenliang Li , Siliang Zeng , Zeyi Liao , Jiaxiang Li , Dongyeop Kang , Alfredo Garcia , Mingyi Hong

Modern alignment pipelines are increasingly replacing expensive human preference labels with evaluations from large language models (LLM-as-Judge). However, AI labels can be systematically biased compared to high-quality human feedback…

Machine Learning · Statistics 2026-02-10 Xintao Xia , Zhiqiu Xia , Linjun Zhang , Zhanrui Cai

We introduce MotionRL, the first approach to utilize Multi-Reward Reinforcement Learning (RL) for optimizing text-to-motion generation tasks and aligning them with human preferences. Previous works focused on improving numerical performance…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Xiaoyang Liu , Yunyao Mao , Wengang Zhou , Houqiang Li

Streaming autoregressive (AR) video generators combined with few-step distillation achieve low-latency, high-quality synthesis, yet remain difficult to align via reinforcement learning from human feedback (RLHF). Existing SDE-based GRPO…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Dailan He , Guanlin Feng , Xingtong Ge , Yi Zhang , Bingqi Ma , Guanglu Song , Yu Liu , Hongsheng Li

For a general-purpose robot to operate in reality, executing a broad range of instructions across various environments is imperative. Central to the reinforcement learning and planning for such robotic agents is a generalizable reward…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Yanting Yang , Minghao Chen , Qibo Qiu , Jiahao Wu , Wenxiao Wang , Binbin Lin , Ziyu Guan , Xiaofei He

Video generation has advanced rapidly, improving evaluation methods, yet assessing video's motion remains a major challenge. Specifically, there are two key issues: 1) current motion metrics do not fully align with human perceptions; 2) the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Xinran Ling , Chen Zhu , Meiqi Wu , Hangyu Li , Xiaokun Feng , Cundian Yang , Aiming Hao , Jiashu Zhu , Jiahong Wu , Xiangxiang Chu

Reward models (RMs) are essential for aligning large language models (LLMs) with human preferences to improve interaction quality. However, the real world is pluralistic, which leads to diversified human preferences with respect to…

Computation and Language · Computer Science 2023-09-18 Pengyu Cheng , Jiawen Xie , Ke Bai , Yong Dai , Nan Du

Animated movies are captivating for their unique character designs and imaginative storytelling, yet they pose significant challenges for existing recognition systems. Unlike the consistent visual patterns detected by conventional face…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Zhongrui Gui , Junyu Xie , Tengda Han , Weidi Xie , Andrew Zisserman

Social reward as a form of community recognition provides a strong source of motivation for users of online platforms to engage and contribute with content. The recent progress of text-conditioned image synthesis has ushered in a…

Computer Vision and Pattern Recognition · Computer Science 2024-02-16 Arman Isajanyan , Artur Shatveryan , David Kocharyan , Zhangyang Wang , Humphrey Shi

Research on diffusion model-based video generation has advanced rapidly. However, limitations in object fidelity and generation length hinder its practical applications. Additionally, specific domains like animated wallpapers require…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Fanyi Wang , Peng Liu , Haotian Hu , Dan Meng , Jingwen Su , Jinjin Xu , Yanhao Zhang , Xiaoming Ren , Zhiwang Zhang

Current alignment pipelines presume a single, universal notion of desirable behavior. However, human preferences often diverge across users, contexts, and cultures. As a result, disagreement collapses into the majority signal and minority…

Machine Learning · Computer Science 2025-06-10 Daniel Halpern , Evi Micha , Ariel D. Procaccia , Itai Shapira

Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Preeti Lamba , Kiran Ravish , Ankita Kushwaha , Pawan Kumar

Recent advancements in audio-video joint generation models have demonstrated impressive capabilities in content creation. However, generating high-fidelity human-centric videos in complex, real-world physical scenes remains a significant…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Lei Zhu , Xing Cai , Yingjie Chen , Yiheng Li , Binxin Yang , Hao Liu , Jie Chen , Chen Li , Jing LYu

Large-scale alignment pipelines typically pair a policy model with a separately trained reward model whose parameters remain frozen during reinforcement learning (RL). This separation creates a complex, resource-intensive pipeline and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Songshuo Lu , Hua Wang , Zhi Chen , Yaohua Tang

The remarkable progress in text-to-video diffusion models enables the generation of photorealistic videos, although the content of these generated videos often includes unnatural movement or deformation, reverse playback, and motionless…

Computer Vision and Pattern Recognition · Computer Science 2025-10-08 Yuta Oshima , Masahiro Suzuki , Yutaka Matsuo , Hiroki Furuta

Bilingual text-to-motion generation, which synthesizes 3D human motions from bilingual text inputs, holds immense potential for cross-linguistic applications in gaming, film, and robotics. However, this task faces critical challenges: the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Wanjiang Weng , Xiaofeng Tan , Hongsong Wang , Pan Zhou

While recent 3D generative models can produce high-quality texture images, they often fail to capture human preferences or meet task-specific requirements. Moreover, a core challenge in the 3D texture generation domain is that most existing…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 AmirHossein Zamani , Tianhao Xie , Amir G. Aghdam , Tiberiu Popa , Eugene Belilovsky

Reward modeling (RM), which captures human preferences to align large language models (LLMs), is increasingly employed in tasks such as model finetuning, response filtering, and ranking. However, due to the inherent complexity of human…

Computation and Language · Computer Science 2026-04-09 Pankayaraj Pathmanathan , Furong Huang

Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences. In the…

Computation and Language · Computer Science 2024-12-19 Zhuoran Jin , Hongbang Yuan , Tianyi Men , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arises because video generation has a complex solution space, and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Mingzhe Zheng , Weijie Kong , Yue Wu , Dengyang Jiang , Yue Ma , Xuanhua He , Bin Lin , Kaixiong Gong , Zhao Zhong , Liefeng Bo , Qifeng Chen , Harry Yang