English
Related papers

Related papers: Reward-Forcing: Autoregressive Video Generation wi…

200 papers

Reinforcement learning usually uses the feedback rewards of environmental to train agents. But the rewards in the actual environment are sparse, and even some environments will not rewards. Most of the current methods are difficult to get…

Machine Learning · Computer Science 2020-01-13 Kai Jiang , XiaoLong Qin

Instructional video generation is an emerging task that aims to synthesize coherent demonstrations of procedural activities from textual descriptions. Such capability has broad implications for content creation, education, and human-AI…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Cheeun Hong , German Barquero , Fadime Sener , Markos Georgopoulos , Edgar Schönfeld , Stefan Popov , Yuming Du , Oscar Mañas , Albert Pumarola

Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike word as token is universally agreed in language if frame is a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Sucheng Ren , Chen Chen , Zhenbang Wang , Liangchen Song , Xiangxin Zhu , Alan Yuille , Yinfei Yang , Jiasen Lu

Aligning video generative models with human preferences remains challenging: current approaches rely on Vision-Language Models (VLMs) for reward modeling, but these models struggle to capture subtle temporal dynamics. We propose a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Shivanshu Shekhar , Uttaran Bhattacharya , Raghavendra Addanki , Mehrab Tanjim , Somdeb Sarkhel , Tong Zhang

Reward-guided text generation (RGTG) has emerged as a viable alternative to offline reinforcement learning from human feedback (RLHF). RGTG methods can align baseline language models to human preferences without further training like in…

Machine Learning · Computer Science 2025-07-08 Ahmad Rashid , Ruotian Wu , Rongqi Fan , Hongliang Li , Agustinus Kristiadi , Pascal Poupart

Real-time motion-controllable video generation remains challenging due to the inherent latency of bidirectional diffusion models and the lack of effective autoregressive (AR) approaches. Existing AR video diffusion models are limited to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Kesen Zhao , Jiaxin Shi , Beier Zhu , Junbao Zhou , Xiaolong Shen , Yuan Zhou , Qianru Sun , Hanwang Zhang

Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on the distance to a target position. However, such precise…

Machine Learning · Computer Science 2025-09-29 Nan Tang , Jing-Cheng Pang , Guanlin Li , Chao Qian , Yang Yu

Text style transfer is an important task in controllable language generation. Supervised approaches have pushed performance improvement on style-oriented rewriting such as formality conversion. However, challenges remain due to the scarcity…

Computation and Language · Computer Science 2022-05-20 Zhengyuan Liu , Nancy F. Chen

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Jaxon Zhang , Binxin Yang , Hubery Yin , Chen Li , Jing Lyu

In human-in-the-loop reinforcement learning or environments where calculating a reward is expensive, the costly rewards can make learning efficiency challenging to achieve. The cost of obtaining feedback from humans or calculating expensive…

Machine Learning · Computer Science 2025-03-03 Muhammed Yusuf Satici , David L. Roberts

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a…

Machine Learning · Computer Science 2023-02-21 Daesol Cho , Seungjae Lee , H. Jin Kim

Score Distillation Sampling (SDS) has emerged as an effective technique for leveraging 2D diffusion priors for tasks such as text-to-3D generation. While powerful, SDS struggles with achieving fine-grained alignment to user intent. To…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Itay Chachy , Guy Yariv , Sagie Benaim

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Siyang Wang , Hanting Li , Wei Li , Jie Hu , Xinghao Chen , Feng Zhao

Reinforcement learning agents learn from rewards, but humans can uniquely assign value to novel, abstract outcomes in a goal-dependent manner. However, this flexibility is cognitively costly, making learning less efficient. Here, we propose…

Neurons and Cognition · Quantitative Biology 2025-09-11 Gaia Molinaro , Anne G. E. Collins

Contemporary recommendation systems are designed to meet users' needs by delivering tailored lists of items that align with their specific demands or interests. In a multi-stage recommendation system, reranking plays a crucial role by…

Information Retrieval · Computer Science 2025-03-26 Yuxin Ren , Qiya Yang , Yichun Wu , Wei Xu , Yalong Wang , Zhiqiang Zhang

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

Computation and Language · Computer Science 2025-09-22 Zhaofeng Wu , Michihiro Yasunaga , Andrew Cohen , Yoon Kim , Asli Celikyilmaz , Marjan Ghazvininejad

Autoregressive transformers have shown remarkable success in video generation. However, the transformers are prohibited from directly learning the long-term dependency in videos due to the quadratic complexity of self-attention, and…

Computer Vision and Pattern Recognition · Computer Science 2023-06-01 Jaehoon Yoo , Semin Kim , Doyup Lee , Chiheon Kim , Seunghoon Hong

Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the…

Robotics · Computer Science 2026-03-25 Ruixiang Wang , Qingming Liu , Yueci Deng , Guiliang Liu , Zhen Liu , Kui Jia

Autoregressive generative models of images tend to be biased towards capturing local structure, and as a result they often produce samples which are lacking in terms of large-scale coherence. To address this, we propose two methods to learn…

Computer Vision and Pattern Recognition · Computer Science 2019-10-09 Jeffrey De Fauw , Sander Dieleman , Karen Simonyan

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Machine Learning · Computer Science 2025-12-30 Amirhossein Tighkhorshid , Zahra Dehghanian , Gholamali Aminian , Chengchun Shi , Hamid R. Rabiee