English
Related papers

Related papers: StepOPSD: Step-Aware Online Preference Distillatio…

200 papers

On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for large language models, especially for reasoning domains. However, OPD remains unstable in practice due to the high gradient variance of its single-sample…

Machine Learning · Computer Science 2026-05-11 Minjae Oh , Sangjun Song , Gyubin Choi , Yunho Choi , Yohan Jo

Multi-agent reinforcement learning typically employs a centralized training-decentralized execution (CTDE) framework to alleviate the non-stationarity in environment. However, the partial observability during execution may lead to…

Multiagent Systems · Computer Science 2025-02-06 Yang Zhou , Siying Wang , Wenyu Chen , Ruoning Zhang , Zhitong Zhao , Zixuan Zhang

The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular approach to address this problem. In this paper, we propose…

Machine Learning · Computer Science 2025-07-09 Ke Jiang , Wen Jiang , Xiaoyang Tan

Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Chaoyang Wang , Yunhai Tong

Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional correctness, and text rendering are weakly specified by score or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yuanzhi Zhu , Xi Wang , Stéphane Lathuilière , Vicky Kalogeiton

Central to the development of universal learning systems is the ability to solve multiple tasks without retraining from scratch when new data arrives. This is crucial because each task requires significant training time. Addressing the…

Machine Learning · Computer Science 2025-01-08 Muhammad Burhan Hafez , Kerim Erekmen

Online Action Detection (OAD) in videos is proposed as a per-frame labeling task to address the real-time prediction tasks that can only obtain the previous and current video frames. This paper presents a novel learning-with-privileged…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Peisen Zhao , Lingxi Xie , Ya Zhang , Yanfeng Wang , Qi Tian

Efficient multi-hop reasoning requires Large Language Models (LLMs) based agents to acquire high-value external knowledge iteratively. Previous work has explored reinforcement learning (RL) to train LLMs to perform search-based document…

Computation and Language · Computer Science 2025-05-27 Ziliang Wang , Xuhui Zheng , Kang An , Cijun Ouyang , Jialu Cai , Yuhang Wang , Yichao Wu

Training autonomous agents with sparse rewards is a long-standing problem in online reinforcement learning (RL), due to low data efficiency. Prior work overcomes this challenge by extracting useful knowledge from offline data, often…

Machine Learning · Computer Science 2024-06-07 Qianlan Yang , Yu-Xiong Wang

Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a single trajectory-level advantage to every token, diluting the signal at pivotal reasoning…

Machine Learning · Computer Science 2026-05-25 Yu Li , Rui Miao , Tian Lan , Zhengling Qi

Large language model-empowered agentic recommender systems (ARS) reformulate recommendation as a multi-turn interaction between a recommender agent and a user agent, enabling iterative preference elicitation and refinement beyond…

Information Retrieval · Computer Science 2026-04-21 Zongwei Wang , Min Gao , Hongzhi Yin , Junliang Yu , Tong Chen , Quoc Viet Hung Nguyen , Shazia Sadiq , Tianrui Li

Diffusion models have achieved impressive results in generative tasks such as text-to-image synthesis, yet they often struggle to fully align outputs with nuanced user intent and maintain consistent aesthetic quality. Existing…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Dohyun Kim , Seungwoo Lyu , Seung Wook Kim , Paul Hongsuck Seo

Recent Knowledge distillation (KD) studies show that different manually designed schemes impact the learned results significantly. Yet, in KD, automatically searching an optimal distillation scheme has not yet been well explored. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-04-13 Xueqing Deng , Dawei Sun , Shawn Newsam , Peng Wang

Human preference alignment presents a critical yet underexplored challenge for diffusion models in text-to-3D generation. Existing solutions typically require task-specific fine-tuning, posing significant hurdles in data-scarce 3D domains.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Jiaqi Leng , Shuyuan Tu , Haidong Cao , Sicheng Xie , Daoguo Dong , Zuxuan Wu , Yu-Gang Jiang

Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental…

Machine Learning · Computer Science 2026-03-24 Jing Liu , Zhenchao Ma , Han Yu , Bobo Ju , Wenliang Yang , Chengfang Li , Bo Hu , Liang Song

Diffusion policies have achieved great success in online reinforcement learning (RL) due to their strong expressive capacity. However, the inference of diffusion policy models relies on a slow iterative sampling process, which limits their…

Machine Learning · Computer Science 2025-10-17 Tianyi Chen , Haitong Ma , Na Li , Kai Wang , Bo Dai

Recent years have witnessed remarkable progress in world models, which primarily aim to capture the spatio-temporal correlations between an agent's actions and the evolving environment. However, existing approaches often suffer from tight…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Guangfeng Jiang , Yueru Luo , Jun Liu , Yi Huang , Yiyao Zhu , Zhan Qu , Dave Zhenyu Chen , Bingbing Liu , Xu Yan

Alignment techniques enable Large Language Models (LLMs) to generate outputs that align with human preferences and play a crucial role in their effectiveness. However, their impact often diminishes when applied to Small Language Models…

Computation and Language · Computer Science 2025-03-06 Shiping Gao , Fanqi Wan , Jiajian Guo , Xiaojun Quan , Qifan Wang

Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Lichen Bai , Zikai Zhou , Shitong Shao , Wenliang Zhong , Shuo Yang , Shuo Chen , Bojun Chen , Zeke Xie

On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-policy distillation can improve a student's output quality…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Ruiqi Liu , Xiaolei Lv , Gengsheng Li , Ximo Zhu , Zhiheng Wang , Zhengbo Zhang , Junkai Chen , Zhiheng Li , Bo Li , Jun Gao , Shu Wu
‹ Prev 1 4 5 6 7 8 10 Next ›