English
Related papers

Related papers: DDA-Thinker: Decoupled Dual-Atomic Reinforcement L…

200 papers

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing audio reasoning rely…

Sound · Computer Science 2026-04-21 Xiang He , Chenxing Li , Jinting Wang , Yan Rong , Tianxin Xie , Wenfu Wang , Li Liu , Dong Yu

Reasoning post-training improves Large Language Models (LLMs) on complex tasks such as mathematics and coding, but its benefits across diverse multimodal tasks remains uncertain. The trend of releasing parallel "Instruct" and "Thinking"…

Computation and Language · Computer Science 2026-05-12 Ruobing Zheng , Tianqi Li , Jianing Li , Qingpei Guo , Yi Yuan , Jingdong Chen

Traditional photographic image editing typically requires users to possess sufficient aesthetic understanding to provide appropriate instructions for adjusting image quality and camera parameters. However, this paradigm relies on explicit…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Ying Zeng , Miaosen Luo , Guangyuan Li , Yang Yang , Ruiyang Fan , Linxiao Shi , Qirui Yang , Jian Zhang , Chengcheng Liu , Siming Zheng , Jinwei Chen , Bo Li , Peng-Tao Jiang

Reasoning models have demonstrated impressive performance on difficult tasks that traditional language models struggle at. However, many are plagued with the problem of overthinking--generating large amounts of unnecessary tokens which…

Computation and Language · Computer Science 2025-04-21 Xiao Pu , Michael Saxon , Wenyue Hua , William Yang Wang

We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers, based on Group Relative Policy Optimization (GRPO). In each pair of training steps, ThinkTwice first…

Artificial Intelligence · Computer Science 2026-04-08 Difan Jiao , Qianfeng Wen , Blair Yang , Zhenwei Tang , Ashton Anderson

DeepSeek-R1 has demonstrated remarkable effectiveness in incentivizing reasoning and generalization capabilities of large language models (LLMs) through reinforcement learning. Nevertheless, the potential of reasoning-induced computation…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Tianhe Wu , Jian Zou , Jie Liang , Lei Zhang , Kede Ma

Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Anirudh Sundara Rajan , Krishna Kumar Singh , Yong Jae Lee

Large Language Models (LLMs) have revolutionized recommendation agents by providing superior reasoning and flexible decision-making capabilities. However, existing methods mainly follow a passive information acquisition paradigm, where…

Information Retrieval · Computer Science 2026-03-11 Haobo Zhang , Yutao Zhu , Kelong Mao , Tianhao Li , Zhicheng Dou

Recent advances in large Vision-Language Models (VLMs) have exhibited strong reasoning capabilities on complex visual tasks by thinking with images in their Chain-of-Thought (CoT), which is achieved by actively invoking tools to analyze…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Wenhao Yang , Yu Xia , Jinlong Huang , Shiyin Lu , Qing-Guo Chen , Zhao Xu , Weihua Luo , Kaifu Zhang , Yuanyu Wan , Lijun Zhang

While large reasoning models trained with critic-free reinforcement learning and verifiable rewards (RLVR) represent the state-of-the-art, their practical utility is hampered by ``overthinking'', a critical issue where models generate…

Computation and Language · Computer Science 2026-03-17 Shuyang Jiang , Yusheng Liao , Ya Zhang , Yanfeng Wang , Yu Wang

Despite the empirical success of extensive, step-by-step reasoning in large multimodal models, long reasoning processes inevitably incur substantial computational overhead, i.e., in terms of higher token costs and increased response time,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-07 Ruiyang Zhang , Dongzhan Zhou , Zhedong Zheng

We address a core problem of computer vision: Detection and description of 2D feature points for image matching. For a long time, hand-crafted designs, like the seminal SIFT algorithm, were unsurpassed in accuracy and efficiency. Recently,…

Computer Vision and Pattern Recognition · Computer Science 2020-03-23 Aritra Bhowmik , Stefan Gumhold , Carsten Rother , Eric Brachmann

Recently, prompt learning has demonstrated remarkable success in adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks such as image classification. However, its application to the downstream Image-Text Retrieval…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Yifan Wang , Tao Wang , Chenwei Tang , Caiyang Yu , Zhengqing Zang , Mengmi Zhang , Shudong Huang , Jiancheng Lv

The field of controllable image generation has seen significant advancements, with various architectures improving generation layout consistency with control signals. However, contemporary methods still face challenges in bridging the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Feng Han , Yang Jiao , Shaoxiang Chen , Junhao Xu , Jingjing Chen , Yu-Gang Jiang

Instruction-based image editing has achieved remarkable progress; however, models solely trained via supervised fine-tuning often overfit to annotated patterns, hindering their ability to explore and generalize beyond training…

Computer Vision and Pattern Recognition · Computer Science 2025-11-05 Zongjian Li , Zheyuan Liu , Qihui Zhang , Bin Lin , Feize Wu , Shenghai Yuan , Zhiyuan Yan , Yang Ye , Wangbo Yu , Yuwei Niu , Shaodong Wang , Xinhua Cheng , Li Yuan

This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making. Inspired by dual-process theory in cognitive science, the representation…

Computation and Language · Computer Science 2022-12-08 Wanjun Zhong , Tingting Ma , Jiahai Wang , Jian Yin , Tiejun Zhao , Chin-Yew Lin , Nan Duan

Recent text-guided image editing (TIE) models have achieved remarkable progress, however, many edited results still suffer from artifacts, unintended modifications, and suboptimal aesthetics. Although several benchmarks and evaluation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Honghua Chen , Zitong Xu , Huiyu Duan , Xinyun Zhang , Xiongkuo Min , Guangtao Zhai

With the rapid advancement of commercial multi-modal models, image editing has garnered significant attention due to its widespread applicability in daily life. Despite impressive progress, existing image editing systems, particularly…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yiran Zhao , Yaoqi Ye , Xiang Liu , Michael Qizhe Shieh , Trung Bui

Recent advancements in Large Language Models (LLMs) have leveraged increased test-time computation to enhance reasoning capabilities, a strategy that, while effective, incurs significant latency and resource costs, limiting their…

Machine Learning · Computer Science 2025-09-01 Hao Wen , Xinrui Wu , Yi Sun , Feifei Zhang , Liye Chen , Jie Wang , Yunxin Liu , Yunhao Liu , Ya-Qin Zhang , Yuanchun Li

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for enhancing reasoning in Large Language Models (LLMs). However, existing reward formulations typically treat exploration and consolidation as a…

Machine Learning · Computer Science 2026-05-15 Wenze Lin , Zhen Yang , Xitai Jiang , Xiaoteng Ma , Gao Huang