中文
相关论文

相关论文: Specificity-aware reinforcement learning for fine-…

200 篇论文

Reinforcement fine-tuning played an instrumental role in enhancing the instruction-following and reasoning abilities of large language models. In this work, we employ reinforcement fine-tuning for materials design, in which discriminative…

材料科学 · 物理学 2026-01-19 Zhendong Cao , Lei Wang

Relational Reinforcement Learning (RRL) can offers various desirable features. Most importantly, it allows for incorporating expert knowledge into the learning, and hence leading to much faster learning and better generalization compared to…

机器学习 · 计算机科学 2020-03-24 Ali Payani , Faramarz Fekri

Large language models provide rich semantic priors and strong reasoning capabilities, making them promising auxiliary signals for recommendation. However, prevailing approaches either deploy LLMs as standalone recommender or apply global…

信息检索 · 计算机科学 2025-12-29 Shanglin Yang , Zhan Shi

Fine-grained image classification, the task of distinguishing between visually similar subcategories within a broader category (e.g., bird species, car models, flower types), is a challenging computer vision problem. Traditional approaches…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Dmitry Demidov , Zaigham Zaheer , Omkar Thawakar , Salman Khan , Fahad Shahbaz Khan

Multimodal large language models (MLLMs) have shown remarkable capabilities in multimodal perception and understanding tasks. However, their effectiveness in specialized domains, such as remote sensing and medical imaging, remains limited.…

计算与语言 · 计算机科学 2026-02-05 Qinglong Cao , Yuntian Chen , Chao Ma , Xiaokang Yang

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning and perceptual abilities for anomaly detection. However, most approaches remain confined to image-level anomaly detection and textual reasoning, while…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Yizhou Jin , Yuezhu Feng , Jinjin Zhang , Peng Wang , Qingjie Liu , Yunhong Wang

Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains a challenging task that often requires substantial manual input. Recently, Large…

机器人学 · 计算机科学 2023-10-03 Jiayang Song , Zhehua Zhou , Jiawei Liu , Chunrong Fang , Zhan Shu , Lei Ma

Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in designing effective and interpretable rewards. Existing methods…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Xuelu Feng , Yunsheng Li , Ziyu Wan , Zixuan Gao , Junsong Yuan , Dongdong Chen , Chunming Qiao

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…

计算机视觉与模式识别 · 计算机科学 2025-12-24 Weijia Wu , Chen Gao , Joya Chen , Kevin Qinghong Lin , Qingwei Meng , Yiming Zhang , Yuke Qiu , Hong Zhou , Mike Zheng Shou

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters…

计算与语言 · 计算机科学 2024-05-31 Kuo Liao , Shuang Li , Meng Zhao , Liqun Liu , Mengge Xue , Zhenyu Hu , Honglin Han , Chengguo Yin

The challenge in fine-grained visual categorization lies in how to explore the subtle differences between different subclasses and achieve accurate discrimination. Previous research has relied on large-scale annotated data and pre-trained…

计算机视觉与模式识别 · 计算机科学 2024-05-16 Tianxu Wu , Shuo Ye , Shuhuang Chen , Qinmu Peng , Xinge You

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Jiahao Xie , Alessio Tonioni , Nathalie Rauschmayr , Federico Tombari , Bernt Schiele

This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically,…

计算机视觉与模式识别 · 计算机科学 2021-06-18 Lucas Caccia , Joelle Pineau

Multi-modal large language models (MLLMs) have shown remarkable abilities in various visual understanding tasks. However, MLLMs still struggle with fine-grained visual recognition (FGVR), which aims to identify subordinate-level categories…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Hulingxiao He , Geng Li , Zijun Geng , Jinglin Xu , Yuxin Peng

Visual entailment is a recently proposed multimodal reasoning task where the goal is to predict the logical relationship of a piece of text to an image. In this paper, we propose an extension of this task, where the goal is to predict the…

计算机视觉与模式识别 · 计算机科学 2022-03-30 Christopher Thomas , Yipeng Zhang , Shih-Fu Chang

Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper…

计算机视觉与模式识别 · 计算机科学 2024-03-14 Shiyu Xuan , Qingpei Guo , Ming Yang , Shiliang Zhang

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for multimodal large language models (MLLMs) have mainly focused on improving final answer correctness and strengthening visual grounding. However, a critical…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Jinda Lu , Junkang Wu , Jinghan Li , Kexin Huang , Shuo Yang , Mingzhu Chen , Jiancan Wu , Kuien Liu , Xiang Wang

Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. While such capability is largely attributed to the rich world…

计算机视觉与模式识别 · 计算机科学 2025-01-08 Jeonghwan Kim , Heng Ji

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Hengjia Li , Liming Jiang , Qing Yan , Yizhi Song , Hao Kang , Zichuan Liu , Xin Lu , Boxi Wu , Deng Cai

Improving large language models (LLMs) for electronic health record (EHR) reasoning is essential for enabling accurate and generalizable clinical predictions. While LLMs excel at medical text understanding, they underperform on EHR-based…