English
Related papers

Related papers: DiffPO: Diffusion-styled Preference Optimization f…

200 papers

While Masked Diffusion Models (MDMs), such as LLaDA, present a promising paradigm for language modeling, there has been relatively little effort in aligning these models with human preferences via reinforcement learning. The challenge…

Machine Learning · Computer Science 2025-10-14 Fengqi Zhu , Rongzhen Wang , Shen Nie , Xiaolu Zhang , Chunwei Wu , Jun Hu , Jun Zhou , Jianfei Chen , Yankai Lin , Ji-Rong Wen , Chongxuan Li

Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of…

Computation and Language · Computer Science 2025-01-24 Guofeng Cui , Pichao Wang , Yang Liu , Zemian Ke , Zhu Liu , Vimal Bhat

Recent advancements in human preference optimization, originally developed for Large Language Models (LLMs), have shown significant potential in improving text-to-image diffusion models. These methods aim to learn the distribution of…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Amir Saeidi , Yiran Luo , Agneet Chatterjee , Shamanthak Hegde , Bimsara Pathiraja , Yezhou Yang , Chitta Baral

Reinforcement Learning with Verifiable Rewards (RLVR) has achieved remarkable success in improving autoregressive models, especially in domains requiring correctness like mathematical reasoning and code generation. However, directly…

Machine Learning · Computer Science 2026-03-03 Chenxing Wei , Jiazhen Kang , Hong Wang , Jianqing Zhang , Hao Jiang , Xiaolong Xu , Ningyuan Sun , Ying He , F. Richard Yu , Yao Shu , Bo Jiang

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data.…

Machine Learning · Computer Science 2024-05-29 Xize Liang , Chao Chen , Shuang Qiu , Jie Wang , Yue Wu , Zhihang Fu , Zhihao Shi , Feng Wu , Jieping Ye

Recent years have seen significant advancements in foundation models through generative pre-training, yet algorithmic innovation in this space has largely stagnated around autoregressive models for discrete signals and diffusion models for…

Machine Learning · Computer Science 2025-03-12 Jiaming Song , Linqi Zhou

Diffusion models have emerged as the leading paradigm in generative modeling, excelling in various applications. Despite their success, these models often misalign with human intentions and generate results with undesired properties or even…

Machine Learning · Computer Science 2026-02-06 Buhua Liu , Shitong Shao , Bao Li , Lichen Bai , Zhiqiang Xu , Haoyi Xiong , James Kwok , Sumi Helal , Zeke Xie

Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation, which in turn presents new challenges for aligning them with human preferences. In this work, we aim to improve the policy optimization for dLLMs by…

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive training of a base model…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Zejian Li , Yize Li , Chenye Meng , Zhongni Liu , Yang Ling , Shengyuan Zhang , Guang Yang , Changyuan Yang , Zhiyuan Yang , Lingyun Sun

Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a…

Computation and Language · Computer Science 2025-06-05 Xiaofeng Zhou , Heyan Huang , Lizi Liao

Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computationally efficient. Vision-Language Models (VLMs) have emerged as the primary reward provider,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Gongye Liu , Bo Yang , Yida Zhi , Zhizhou Zhong , Lei Ke , Didan Deng , Han Gao , Yongxiang Huang , Kaihao Zhang , Hongbo Fu , Wenhan Luo

Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human…

Software Engineering · Computer Science 2025-12-09 Xin Yin , Chao Ni , Xiaohu Yang

Recent studies have shown the great potential of diffusion models in improving reinforcement learning (RL) by modeling complex policies, expressing a high degree of multi-modality, and efficiently handling high-dimensional continuous…

Robotics · Computer Science 2025-05-14 Huiyun Jiang , Zhuang Yang

Many applications of large language models (LLMs), ranging from chatbots to creative writing, require nuanced subjective judgments that can differ significantly across different groups. Existing alignment algorithms can be expensive to…

Machine Learning · Computer Science 2024-10-16 Siyan Zhao , John Dang , Aditya Grover

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Kaixun Jiang , Zhaoyu Chen , Haijing Guo , Jinglun Li , Jiyuan Fu , Pinxue Guo , Hao Tang , Bo Li , Wenqiang Zhang

Preference optimization is crucial for aligning large language models (LLMs) with human values and intentions. A significant challenge in this process is the distribution mismatch between pre-collected offline preference data and the…

Computation and Language · Computer Science 2026-03-02 Junming Yang , Ning Xu , Biao Liu , Shiqi Qiao , Xin Geng

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve…

Computation and Language · Computer Science 2024-11-15 Somanshu Singla , Zhen Wang , Tianyang Liu , Abdullah Ashfaq , Zhiting Hu , Eric P. Xing

Masked diffusion language models generate text through iterative masked-token filling, but terminal-only rewards on final completions provide coarse credit assignment for the intermediate filling decisions that shape the generation process.…

Computation and Language · Computer Science 2026-05-20 Daisuke Oba , Hiroki Furuta , Naoaki Okazaki

We introduce a novel alignment method for diffusion models from distribution optimization perspectives while providing rigorous convergence guarantees. We first formulate the problem as a generic regularized loss minimization over…

Machine Learning · Computer Science 2025-03-07 Ryotaro Kawata , Kazusato Oko , Atsushi Nitanda , Taiji Suzuki

Adapting pretrained diffusion models to downstream objectives such as inverse problems often requires expensive test-time guidance or optimization. We propose a principled framework for generating high-quality reward-aligned samples at…

Machine Learning · Computer Science 2026-05-22 Kushagra Pandey , Farrin Marouf Sofian , Jan Niklas Groeneveld , Felix Draxler , Stephan Mandt