English
Related papers

Related papers: Flow-OPD: On-Policy Distillation for Flow Matching…

200 papers

Flow matching is a recent state-of-the-art framework for generative modeling based on ordinary differential equations (ODEs). While closely related to diffusion models, it provides a more general perspective on generative modeling. Although…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Jeongsol Kim , Bryan Sangwoo Kim , Jong Chul Ye

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number of desired effects grows, storing and dynamically loading…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Fangtai Wu , Hailong Guo , Shijie Huang , Jiayi Song , Yubo Huang , Mushui Liu , Zhao Wang , Yunlong Yu , Jiaming Liu , Ruihua Huang

Recent progress in text-to-3D generation has been achieved through the utilization of score distillation methods: they make use of the pre-trained text-to-image (T2I) diffusion models by distilling via the diffusion model training…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Kyungmin Lee , Kihyuk Sohn , Jinwoo Shin

Flow Matching has emerged as a powerful framework for learning continuous transformations between distributions, enabling high-fidelity generative modeling. This work introduces Symmetrical Flow Matching (SymmFlow), a new formulation that…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Francisco Caetano , Christiaan Viviers , Peter H. N. De With , Fons van der Sommen

On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher, but its standard objective weights all generated tokens equally, implicitly treating the privileged teacher target as equally reliable at…

Machine Learning · Computer Science 2026-05-22 Xiaogeng Liu , Xinyan Wang , Yingzi Ma , Yechao Zhang , Chaowei Xiao

Diffusion models are extensively used for modeling image priors for inverse problems. We introduce \emph{Diff-Unfolding}, a principled framework for learning posterior score functions of \emph{conditional diffusion models} by explicitly…

Image and Video Processing · Electrical Eng. & Systems 2025-05-22 Yuanhao Wang , Shirin Shoushtari , Ulugbek S. Kamilov

Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference…

Machine Learning · Computer Science 2026-03-03 Daniel Ritter , Owen Oertell , Bradley Guo , Jonathan Chang , Kianté Brantley , Wen Sun

Reinforcement Learning (RL) has emerged as a central paradigm for advancing Large Language Models (LLMs), where pre-training and RL post-training share the same log-likelihood formulation. In contrast, recent RL approaches for diffusion…

Machine Learning · Computer Science 2025-09-30 Shuchen Xue , Chongjian Ge , Shilong Zhang , Yichen Li , Zhi-Ming Ma

Generative Flow Networks (GFlowNets) are amortized samplers that learn stochastic policies to sequentially generate compositional objects from a given unnormalized reward distribution. They can generate diverse sets of high-reward objects,…

Machine Learning · Computer Science 2023-10-06 Ling Pan , Moksh Jain , Kanika Madan , Yoshua Bengio

Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-04 Yiwei Guo , Chenpeng Du , Ziyang Ma , Xie Chen , Kai Yu

Large vision-language models have achieved outstanding performance, but their size and computational requirements make their deployment on resource-constrained devices and time-sensitive tasks impractical. Model distillation, the process of…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 Xuanlin Li , Yunhao Fang , Minghua Liu , Zhan Ling , Zhuowen Tu , Hao Su

Recent deep metric learning (DML) methods typically leverage solely class labels to keep positive samples far away from negative ones. However, this type of method normally ignores the crucial knowledge hidden in the data (e.g., intra-class…

Computer Vision and Pattern Recognition · Computer Science 2022-11-15 Zelong Zeng , Fan Yang , Hong Liu , Shin'ichi Satoh

Learning from expert demonstrations is a promising approach for training robotic manipulation policies from limited data. However, imitation learning algorithms require a number of design choices ranging from the input modality, training…

Robotics · Computer Science 2024-09-12 Eugenio Chisari , Nick Heppert , Max Argus , Tim Welschehold , Thomas Brox , Abhinav Valada

Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy…

Machine Learning · Computer Science 2026-05-29 Yan Chen , Taojie Zhu , Meng Zhang , Xin Chen , Jiaqi Huang , Dongyang Xu , Yizhi Wang

Online on-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts. We provide a theoretical explanation for this phenomenon…

Machine Learning · Computer Science 2026-01-14 Juno Kim , Jihun Yun , Jason D. Lee , Kwang-Sung Jun

Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vision--language models derived from them recover bidirectional capability through…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Eric Tillmann Bill , Enis Simsar , Alessio Tonioni , Thomas Hofmann

Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scenarios, it remains the inevitable challenge due to the gap…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 Siyuan Du , Yuhang Zhou , Haolin Li , Jiangchao Yao , Haishuai Wang , Hui Lin , Ya Zhang , Yanfeng Wang

Diffusion models have shown remarkable progress in text-to-audio generation. However, text-guided audio editing remains in its early stages. This task focuses on modifying the target content within an audio signal while preserving the rest,…

Sound · Computer Science 2026-04-17 Liting Gao , Yi Yuan , Yaru Chen , Yuelan Cheng , Zhenbo Li , Juan Wen , Shubin Zhang , Wenwu Wang

Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is…

Machine Learning · Computer Science 2020-06-09 Kwei-Herng Lai , Daochen Zha , Yuening Li , Xia Hu
‹ Prev 1 8 9 10 Next ›