Existing LLM test-time scaling laws emphasize the emergence of self-reflective behaviors through extended reasoning length. Nevertheless, this vertical scaling strategy often encounters plateaus in exploration as the model becomes locked into specific thinking pattern. By shifting from depth to parallelism, parallel thinking mitigates the narrowing of exploration. However, the extension of this paradigm to visual domain remains an open research question. In this paper, we first examine the role of visual partitioning in parallelized reasoning and subsequently propose two distinct strategies. Based on the above, we introduce Visual Para-Thinker, representing the inaugural parallel reasoning framework for MLLMs. To maintain path independence and promote diversity in reasoning, our approach integrates Pa-Attention alongside LPRoPE. Leveraging the vLLM framework, we have developed a native multimodal implementation that facilitates high-efficiency parallel processing. Empirical results on benchmark datasets such as V*, CountBench, RefCOCO, and HallusionBench confirm that Visual Para-Thinker successfully extends the benefits of parallel reasoning to the visual domain.
Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning
Zhejiang University(浙江大学);Hunan University(湖南大学);Tianjin University(天津大学);University of Chinese Academy of Sciences(中国科学院大学);Shanghai Jiao Tong University(上海交通大学);Jilin University(吉林大学)
The Cultural Psychology of Large Language Models: Is ChatGPT a Holistic or Analytic Thinker?
New York University(纽约大学);University of Chicago(芝加哥大学);Massachusetts Institute of Technology(麻省理工学院);Johns Hopkins University(约翰斯·霍普金斯大学);University of California Los Angeles(加州大学洛杉矶分校)
Divide-and-Conquer Inference for Large-Scale Visual Recognition with Multimodal Large Language Models
Taizhou Institute of Science and Technology, Nanjing University of Science and Technology(泰州科技学院、南京理工大学);Department of Intelligence Science, Xi’an Jiaotong-Liverpool University(智能科学系,西安交通大学利物浦大学);School of Computer Science and Technology, Soochow University(计算机科学与技术学院,苏州大学);Department of Statistical Sciences, University of Toronto(统计科学系,多伦多大学)
Indoor Panorama Planar 3D Reconstruction via Divide and Conquer
National Tsing Hua University(国立清华大学);ASUS AICS(华硕AI研发中心);Joint Research Center for AI Technology and All Vista Healthcare(AI技术与All Vista Healthcare联合研究中心);Aeolus Robotics
Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene
Shenzhen Graduate School, Peking University(北京大学深圳研究生院);Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology(广东省超高清沉浸式媒体技术重点实验室)
A Divide-and-Conquer Approach towards Understanding Deep Networks
Friedrich-Alexander University Erlangen-Nürnberg(埃尔朗根-纽伦堡弗里德里希-亚历山大大学);Erlangen Graduate School in Advanced Optical Technologies(埃尔朗根先进光学技术研究生院)
深度神经网络在包括医学图像分割在内的各个领域都取得了巨大的成功。然而,它们长期以来一直被批评为黑箱,因为解释,理解和纠正架构是困难的,因为没有深层神经网络设计的通用理论。以前,精确学习被提出来融合深度架构和传统方法。以这种方式构建的深度网络受益于原始的已知算子,具有更少的参数,并提高了可解释性。然而,它们并不能在所有应用中产生最先进的性能。在本文中,我们建议使用已知的运营商来分析深度网络,通过采用分而治之的策略来替换网络组件,同时保持其性能。视网膜血管分割的任务是为此目的进行研究。我们从一个高性能的U-Net开始,并通过一步一步的转换表明,我们能够将网络划分为已知运营商的模块。结果表明,可训练引导滤波器和Frangi滤波器的可训练版本的组合在U-Net水平上产生性能(AUC 0.974 vs. 0.972),参数大幅减少(111,536 vs. 9,575)。此外,经过训练的层可以映射回其原始算法解释,并使用标准的信号处理工具进行分析。
PDC-Net: Pattern Divide-and-Conquer Network for Pelvic Radiation Injury Segmentation
School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);Department of Radiology, The Sixth Affiliated Hospital, Sun Yat-sen University(中山大学第六附属医院放射科);School of Computer and Information Engineering, Jiangxi Normal University(江西师范大学计算机与信息工程学院);Department of General Surgery, The Sixth Affiliated Hospital, Sun Yat-sen University(中山大学第六附属医院普外科);Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases, Biomedical Innovation Center, The Sixth Affiliated Hospital, Sun Yat-sen University(广东省直肠及盆底疾病重点实验室,生物医学创新中心,中山大学第六附属医院)
Efficient divide-and-conquer registration of UAV and ground LiDAR point clouds through canopy shape context
School of Geospatial Engineering and Science, Sun Yat-Sen University(中山大学测绘科学与技术学院);Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University(香港理工大学土地测量及地理资讯学系);Changjiang River Scientific Research Institute (CRSRI)(长江水利委员会长江科学院);Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院数字地球重点实验室);Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)(南方海洋科学与工程广东省实验室(珠海))
Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection
School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);Department of Computer Science and Engineering, The Hong Kong University of Science and Technology(香港科技大学计算机科学与工程系);School of Computing and Information Systems, Singapore Management University(新加坡管理大学计算与信息系统学院)