English
Related papers

Related papers: OSPO: Object-Centric Self-Improving Preference Opt…

200 papers

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Tao Zhang , Cheng Da , Kun Ding , Huan Yang , Kun Jin , Yan Li , Tingting Gao , Di Zhang , Shiming Xiang , Chunhong Pan

Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date. Despite their success, existing methods…

Computation and Language · Computer Science 2025-07-01 Kyuyoung Kim , Ah Jeong Seo , Hao Liu , Jinwoo Shin , Kimin Lee

With the rapid progress of Multimodal Large Language Models (MLLMs), unified MLLMs that jointly perform image understanding and generation have advanced significantly. However, despite the inherent reasoning capabilities of unified MLLMs…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Yongjin Kim , Yoonjin Oh , Yerin Kim , Hyomin Kim , Jeeyoung Yun , Yujung Heo , Minjun Kim , Sungwoong Kim

Large Language Models (LLMs) often suffer from hallucinations: output content that is not grounded in the input context, when performing long-form text generation tasks such as summarization. Prior works have shown that hallucinations can…

Computation and Language · Computer Science 2025-12-23 Ting-Yao Hu , Hema Swetha Koppula , Hadi Pouransari , Cem Koc , Oncel Tuzel , Raviteja Vemulapalli

Multi-modal large language models (MLLMs) are expected to support multi-turn queries of interchanging image and text modalities in production. However, the current MLLMs trained with visual-question-answering (VQA) datasets could suffer…

Computation and Language · Computer Science 2024-11-06 Shengzhi Li , Rongyu Lin , Shichao Pei

Multi-Objective Alignment (MOA) aims to align LLMs' responses with multiple human preference objectives, with Direct Preference Optimization (DPO) emerging as a prominent approach. However, we find that DPO-based MOA approaches suffer from…

Machine Learning · Computer Science 2025-12-09 Moxin Li , Yuantao Zhang , Wenjie Wang , Wentao Shi , Zhuo Liu , Fuli Feng , Tat-Seng Chua

While Audio-Visual Language Models (AVLMs) have achieved remarkable progress over recent years, their reliability is bottlenecked by cross-modal hallucination. A particularly pervasive manifestation is video-driven audio hallucination:…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Ami Baid , Zihui Xue , Kristen Grauman

Pre-trained vision-language models like CLIP have remarkably adapted to various downstream tasks. Nonetheless, their performance heavily depends on the specificity of the input text prompts, which requires skillful prompt template…

Machine Learning · Computer Science 2024-10-22 Yingjun Du , Wenfang Sun , Cees G. M. Snoek

The success of Direct Preference Optimization (DPO) in mitigating hallucinations in Vision Language Models (VLMs) critically hinges on the true reward gaps within preference pairs. However, current methods, typically relying on ranking or…

Computation and Language · Computer Science 2025-11-25 Lehan He , Zeren Chen , Zhelun Shi , Tianyu Yu , Jing Shao , Lu Sheng

For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…

Artificial Intelligence · Computer Science 2025-05-27 Anirudhan Badrinath , Prabhat Agarwal , Jiajing Xu

Large language models are increasingly trained via reinforcement learning for personalized recommendation tasks, but standard methods like GRPO rely on sparse, sequence-level rewards. These obscure which tokens actually contribute to…

Artificial Intelligence · Computer Science 2026-05-08 Abhijnan Nath , Alireza Bagheri Garakani , Tianchen Zhou , Fan Yang , Yan Gao , Nikhil Krishnaswamy

Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct…

Computation and Language · Computer Science 2025-07-08 Archiki Prasad , Weizhe Yuan , Richard Yuanzhe Pang , Jing Xu , Maryam Fazel-Zarandi , Mohit Bansal , Sainbayar Sukhbaatar , Jason Weston , Jane Yu

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

Large Visual Language Models (LVLMs) increasingly rely on preference alignment to ensure reliability, which steers the model behavior via preference fine-tuning on preference data structured as ``image - winner text - loser text'' triplets.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-10 Kejia Chen , Jiawen Zhang , Jiacong Hu , Jiazhen Yang , Jian Lou , Zunlei Feng , Mingli Song

Reinforcement Learning with Human Feedback (RLHF) enhances the alignment of Large Language Models (LLMs). However, its limitations have led to the development of Direct Preference Optimization (DPO), an RL-free approach designed to overcome…

Computation and Language · Computer Science 2025-02-19 Amir Saeidi , Shivanshu Verma , Aswin RRV , Kashif Rasul , Chitta Baral

Multimodal large language models (MLLMs) have recently achieved impressive general-purpose vision-language capabilities through visual instruction tuning. However, current MLLMs primarily focus on image-level or box-level understanding,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Yuqian Yuan , Wentong Li , Jian Liu , Dongqi Tang , Xinjie Luo , Chi Qin , Lei Zhang , Jianke Zhu

Instruction-following Vision Large Language Models (VLLMs) have achieved significant progress recently on a variety of tasks. These approaches merge strong pre-trained vision models and large language models (LLMs). Since these components…

Machine Learning · Computer Science 2024-02-20 Yiyang Zhou , Chenhang Cui , Rafael Rafailov , Chelsea Finn , Huaxiu Yao

Direct Preference Optimization (DPO) is broadly utilized for aligning Large Language Models (LLMs) with human values because of its flexibility. Despite its effectiveness, it has been observed that the capability of DPO to generate…

Machine Learning · Computer Science 2025-05-20 Wenqiao Zhu , Ji Liu , Lulu Wang , Jun Wu , Yulun Zhang

Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitations in existing attention mechanisms and insufficient…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Xiaochen Yang , Hao Fang , Jiawei Kong , Yaoxin Mao , Bin Chen , Shu-Tao Xia

Direct Preference Optimization (DPO) and its variants have become standard for aligning Large Language Models due to their simplicity and offline stability. However, we identify two fundamental limitations. First, the optimal policy depends…

Artificial Intelligence · Computer Science 2026-02-10 Yu Li , Tian Lan , Zhengling Qi
‹ Prev 1 4 5 6 7 8 10 Next ›