English
Related papers

Related papers: Controlling Multimodal LLMs via Reward-guided Deco…

200 papers

Despite the great success of Large Vision-Language Models (LVLMs), they inevitably suffer from hallucination. As we know, both the visual encoder and the Large Language Model (LLM) decoder in LVLMs are Transformer-based, allowing the model…

Computation and Language · Computer Science 2025-11-07 Xuan Gong , Tianshi Ming , Xinpeng Wang , Zhihua Wei

Large Language Models (LLMs) have made substantial strides in structured tasks through Reinforcement Learning (RL), demonstrating proficiency in mathematical reasoning and code generation. However, applying RL in broader domains like…

Computation and Language · Computer Science 2025-02-10 Hao Sun , Yunyi Shen , Jean-Francois Ton , Mihaela van der Schaar

Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucinations-generating content that is inconsistent with the input image. Existing training-free hallucination mitigation methods…

Machine Learning · Computer Science 2025-05-20 Kai Tang , Jinhao You , Xiuqi Ge , Hanze Li , Yichen Guo , Xiande Huang

Large vision-language models (LVLMs) have made significant progress in recent years. While LVLMs exhibit excellent ability in language understanding, question answering, and conversations of visual inputs, they are prone to producing…

Computation and Language · Computer Science 2024-11-20 Qing Li , Jiahui Geng , Chenyang Lyu , Derui Zhu , Maxim Panov , Fakhri Karray

The multi-objective alignment of Large Language Models (LLMs) is essential for ensuring foundational models conform to diverse human preferences. Current research in this field typically involves either multiple policies or multiple reward…

Computation and Language · Computer Science 2025-05-28 Yu Zhang , Wanli Jiang , Zhengyu Yang

State-of-the-art large language models (LLMs) have become indispensable tools for various tasks. However, training LLMs to serve as effective assistants for humans requires careful consideration. A promising approach is reinforcement…

Multimodal large language models (MLLM) have achieved satisfactory results in many tasks. However, their performance in the task of ReID (ReID) has not been explored to date. This paper will investigate how to adapt them for the task of…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Shan Yang , Yongfei Zhang

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

We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combines a lightweight draft model with a more powerful target…

Computation and Language · Computer Science 2025-06-27 Baohao Liao , Yuhui Xu , Hanze Dong , Junnan Li , Christof Monz , Silvio Savarese , Doyen Sahoo , Caiming Xiong

Although vision models such as Contrastive Language-Image Pre-Training (CLIP) show impressive generalization performance, their zero-shot robustness is still limited under Out-of-Distribution (OOD) scenarios without fine-tuning. Instead of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Zhuo Huang , Chang Liu , Yinpeng Dong , Hang Su , Shibao Zheng , Tongliang Liu

Although Large Language Models (LLMs) excel in reasoning and generation for language tasks, they are not specifically designed for multimodal challenges. Training Multimodal Large Language Models (MLLMs), however, is resource-intensive and…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Yuqi Pang , Bowen Yang , Haoqin Tu , Yun Cao , Zeyu Zhang

Large Vision-Language Models (VLMs) often exhibit text inertia, where attention drifts from visual evidence toward linguistic priors, resulting in object hallucinations. Existing decoding strategies intervene only at the output logits and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Weijue Bu , Guan Yuan , Guixian Zhang

Contrastive decoding strategies are widely used to reduce object hallucinations in multimodal large language models (MLLMs). These methods work by constructing contrastive samples to induce hallucinations and then suppressing them in the…

Computation and Language · Computer Science 2025-10-08 Hao Yin , Guangzong Si , Zilei Wang

In this paper, we advance the study of AI-augmented reasoning in the context of Human-Computer Interaction (HCI), psychology and cognitive science, focusing on the critical task of visual perception. Specifically, we investigate the…

Human-Computer Interaction · Computer Science 2025-04-18 Shravan Chaudhari , Trilokya Akula , Yoon Kim , Tom Blake

By combining natural language understanding, generation capabilities, and breadth of knowledge of large language models with image perception, recent large vision language models (LVLMs) have shown unprecedented visual reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Siming Yan , Min Bai , Weifeng Chen , Xiong Zhou , Qixing Huang , Li Erran Li

Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields. However, LLMs are prone to hallucinate untruthful or nonsensical outputs that fail to meet user expectations in many…

Computation and Language · Computer Science 2023-11-23 Tianhang Zhang , Lin Qiu , Qipeng Guo , Cheng Deng , Yue Zhang , Zheng Zhang , Chenghu Zhou , Xinbing Wang , Luoyi Fu

Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual information. This paper presents a comprehensive analysis of…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Shweta Mahajan , Hoang Le , Hyojin Park , Farzad Farhadzadeh , Munawar Hayat , Fatih Porikli

Reward engineering, the manual specification of reward functions to induce desired agent behavior, remains a fundamental challenge in multi-agent reinforcement learning. This difficulty is amplified by credit assignment ambiguity,…

Artificial Intelligence · Computer Science 2026-01-14 Haoran Su , Yandong Sun , Congjia Yu

Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with…

Computation and Language · Computer Science 2024-03-21 Haozhe Zhao , Zefan Cai , Shuzheng Si , Xiaojian Ma , Kaikai An , Liang Chen , Zixuan Liu , Sheng Wang , Wenjuan Han , Baobao Chang

Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward functions. In this paper, we propose a…

Robotics · Computer Science 2026-03-24 Yanru Wu , Weiduo Yuan , Ang Qi , Vitor Guizilini , Jiageng Mao , Yue Wang