English
Related papers

Related papers: CHiP: Cross-modal Hierarchical Direct Preference O…

200 papers

The alt-text generation task produces concise, context-relevant descriptions of images, enabling blind and low-vision users to access online images. Despite the capabilities of large vision-language models, alt-text generation performance…

Computation and Language · Computer Science 2025-10-02 Jinlan Fu , Shenzhen Huangfu , Hao Fei , Yichong Huang , Xiaoyu Shen , Xipeng Qiu , See-Kiong Ng

Direct Preference Optimization (DPO) has become the de facto standard for offline preference alignment of large language models, but its reliance on a reference policy introduces a critical tension. DPO weighs each update relative to a…

Machine Learning · Computer Science 2026-02-13 Suqin Yuan , Xingrui Yu , Jiyang Zheng , Lei Feng , Dadong Wang , Ivor Tsang , Tongliang Liu

Aligning language models (LMs) with curated human feedback is critical to control their behaviors in real-world applications. Several recent policy optimization methods, such as DPO and SLiC, serve as promising alternatives to the…

Computation and Language · Computer Science 2025-01-28 Tianqi Liu , Zhen Qin , Junru Wu , Jiaming Shen , Misha Khalman , Rishabh Joshi , Yao Zhao , Mohammad Saleh , Simon Baumgartner , Jialu Liu , Peter J. Liu , Xuanhui Wang

Multimodal large language models (MLLMs) have demonstrated impressive performance in various vision-language (VL) tasks, but their expensive computations still limit the real-world application. To address this issue, recent efforts aim to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Hao Ai , Kunyi Wang , Zezhou Wang , Hao Lu , Jin Tian , Yaxin Luo , Peng Xing , Jen-Yuan Huang , Huaxia Li , Gen luo

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

Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Massimiliano Pappa , Luca Collorone , Giovanni Ficarra , Indro Spinelli , Fabio Galasso

Large Vision-Language Models (LVLMs) are susceptible to object hallucinations, an issue in which their generated text contains non-existent objects, greatly limiting their reliability and practicality. Current approaches often rely on the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Ailin Deng , Zhirui Chen , Bryan Hooi

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

Large Vision-Language Models (LVLMs) are increasingly adept at generating contextually detailed and coherent responses from visual inputs. However, their application in multimodal decision-making and open-ended generation is hindered by a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Xintong Wang , Jingheng Pan , Liang Ding , Chris Biemann

Medical Vision-Language Models (VLMs) are prone to hallucinations, compromising clinical reliability. While reinforcement learning methods like Group Relative Policy Optimization (GRPO) offer a low-cost alignment solution, their reliance on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Xiao Liang , Yuxuan An , Di Wang , Jiawei Hu , Zhicheng Jiao , Bin Jing , Quan Wang

Large vision-language models have become widely adopted to advance in various domains. However, developing a trustworthy system with minimal interpretable characteristics of large-scale models presents a significant challenge. One of the…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Huu-Thien Tran , Thanh-Dat Truong , Khoa Luu

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

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement…

Computation and Language · Computer Science 2024-12-10 Junru Lu , Jiazheng Li , Siyu An , Meng Zhao , Yulan He , Di Yin , Xing Sun

Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler approach that…

Machine Learning · Computer Science 2026-01-27 Saeed Najafi , Alona Fyshe

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal task reasoning. However, they often generate responses that appear plausible yet do not accurately reflect the visual content, a phenomenon known…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Jiaqi Wang , Yifei Gao , Jitao Sang

Native Omni-modal Large Language Models (OLLMs) have shifted from pipeline architectures to unified representation spaces. However, this native integration gives rise to a critical yet underexplored phenomenon: modality preference. To…

Artificial Intelligence · Computer Science 2026-04-30 Xinru Yan , Boxi Cao , Yaojie Lu , Hongyu Lin , Weixiang Zhou , Le Sun , Xianpei Han

Hallucinations in Large Language Models (LLMs) are widely regarded as errors - outputs that deviate from factual accuracy. However, in creative or exploratory contexts, these "mistakes" may represent unexpected avenues for innovation. We…

Artificial Intelligence · Computer Science 2025-04-17 Kris Pilcher , Esen K. Tütüncü

Contrastive Language-Image Pre-training (CLIP), which excels at abstracting open-world representations across domains and modalities, has become a foundation for a variety of vision and multimodal tasks. However, recent studies reveal that…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Wenxuan Wang , Quan Sun , Fan Zhang , Yepeng Tang , Jing Liu , Xinlong Wang

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled them to effectively integrate vision and language, addressing a variety of downstream tasks. However, despite their significant success, these models still exhibit…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Zixian Gao , Chao Yang , Zhanhui Zhou , Xing Xu , Chaochao Lu

Human preference alignment is critical in building powerful and reliable large language models (LLMs). However, current methods either ignore the multi-dimensionality of human preferences (e.g. helpfulness and harmlessness) or struggle with…

Machine Learning · Computer Science 2024-10-14 Xingzhou Lou , Junge Zhang , Jian Xie , Lifeng Liu , Dong Yan , Kaiqi Huang
‹ Prev 1 8 9 10 Next ›