PAPER EVIDENCE RANKING

论文证据排行榜

基于PaperMiner证据链动态评分。缺失证据保持未知，不等同于零分；不同任务论文不宜只凭总分直接比较。

综合侧重 科研价值 工程落地 综合影响
单项维度 可信度 可复现性 实验充分度 创新性 工程价值 影响力
评分版本：paper-evidence-v3 最低证据覆盖率：35%
排名 论文 得分 主要署名单位 任务 / 年份 覆盖率
1 Spiking Variational Graph Representation Inference for Video Summarization 70.1 Harbin Institute of Technology, University of Electronic Science and Technology of China, Peking University 未分类 · 2025 90%
2 Real-Time Underwater Image Enhancement via Frequency-Guided Dual-Path Attention 70.1 Glasgow College, UESTC; University of Glasgow 图像增强 · 2026 90%
3 A Unified Candidate Set with Scene-Adaptive Refinement via Diffusion for End-to-End Autonomous Driving 70.1 未明确提供，推测为作者所属机构 自动驾驶 · 2026 90%
4 Unified Diffusion Refinement for Multi-Channel Speech Enhancement and Separation 70.1 IEEE 语音增强 · 2026 90%
5 More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era 70.1 School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China (USTC), Hefei Anhui, 230026, China; Center for Medical Imaging, Robotics, Analytic Computing & Learning (MIRACLE), Suzhou Institute for Advance Research, USTC, Suzhou Jiangsu, 215123, China; The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, USTC, Hefei Anhui, 230001, China; Jiangsu Provincial Key Laboratory of Multimodal Digital Twin Technology, Suzhou Jiangsu, 215123, China; State Key Laboratory of Precision and Intelligent Chemistry, USTC, Hefei Anhui 230026, China 未分类 · 2025 90%
6 Stability of Transformers under Layer Normalization 70.1 UCLA, UT Austin, UNC Chapel Hill, SRI International, UMass Amherst 模型架构 · 2025 90%
7 Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling 70.1 Korea University, Kakao Mobility 自动驾驶 · 2026 90%
8 RPBA-Net: An Interpretable Residual Pyramid Bilateral Affine Network for RAW-Domain ISP Enhancement 70.1 未明确给出，但作者 affiliations 中可能包括高校或研究机构，需后续查询 图像增强 · 2026 90%
9 DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation 70.1 SAI, Shanghai Jiao Tong University, Shanghai, China 数据集 · 2026 90%
10 SinAE: A Single-Architecture Flow-Matching Autoencoder for Cross-Domain Atomic Systems 69.82 National University of Singapore, Tencent AI for Life Science Lab 人工智能 · 2026 100%
11 VTaMo: Video-Text Alignment Model for Sign Language Translation 69.82 New York University Abu Dhabi, ChatSign Technology 多模态 · 2026 100%
12 VLA-ReID: Video-Level Association for Re-Identification in Multi-Object Tracking with Highly Similar Objects 69.82 University of Electronic Science and Technology of China, Peking University Shenzhen Graduate School, Chongqing University 目标跟踪 · 2026 100%
13 Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention 69.82 上海交通大学，福州大学，上海人工智能实验室 图像恢复 · 2026 100%
14 ID-V2V: Identity-Preserving Video Restylization 69.82 Netflix, United States of America; Eyeline Labs, United States of America; Adobe, United States of America 视频生成 · 2026 90%
15 Overcoming Attention Drift: Homogeneity-Heterogeneity Guided Feature Aggregation for Low-Light Remote Sensing Image Enhancement 69.82 未知 图像增强 · 2026 90%
16 LDFE: Laplacian Decoupled Feature Enhancement Block for Dual-Stream CNN-based RGB-IR Object Detection 69.82 Beihang University, Communication University of China, Zhongguancun Academy, Eastern Institute of Technology, Beijing Institute of Control and Electronics Technology 图像增强 · 2026 90%
17 DepthAnything and SAM for UIE: Exploring Large Model Information Contributes to Underwater Image Restoration 69.68 Sun Yat-sen University, Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) 图像增强 100%
18 LPM: Industrial-Scale Generative Video Restoration 69.61 Kuaishou Technology 视频生成 · 2026 90%
19 From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark 69.53 IEEE Member, Fellow, IEEE, † 图像恢复 · 2026 100%
20 DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation 69.53 Zhejiang University 未分类 · 2025 100%
21 A Reinforcement Learning Approach to Synthetic Data Generation 69.53 Princeton University, Vanderbilt University Medical Center, Washington University AI医疗 · 2025 100%
22 Collaborative Feature Aggregation for Face Super-Resolution and Robust Re-Identification 69.53 Yonsei University, Dongduk Women’s University, Sookmyung Women’s University 图像恢复 · 2026 100%
23 LoL: Longer than Longer, Scaling Video Generation to Hour 69.53 UCLA, ByteDance Seed, University of Central Florida 视频生成 · 2026 100%
24 MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark 69.53 Cornell University 数据集 100%
25 A Physically-Grounded Attack and Adaptive Defense Framework for Real-World Low-Light Image Enhancement 69.53 未明确提供，作者信息中仅显示IEEE Senior Member，推测为相关研究机构或高校 图像增强 · 2026 90%
26 DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion 69.53 1 School of Mechanical Engineering, Dalian University of Technology; 2 School of Software Technology & DUT-RU International School of ISE, Dalian University of Technology; 3 School of Computer Science, Northwestern Polytechnical University; 4 College of Information Science and Technology, Dalian Maritime University 图像增强 · 2025 90%
27 Entity-Guided Multi-Task Learning for Infrared and Visible Image Fusion 69.53 未明确 图像融合 · 2026 90%
28 V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation 69.53 UNC Chapel Hill, Adobe Research 视频生成 · 2026 90%
29 GENERATIVE MARKET EQUILIBRIUM MODELS WITH STABLE ADVERSARIAL LEARNING VIA REINFORCEMENT LINK 69.53 未明确提供 AI金融 · 2025 90%
30 DRIVINGGEN: A COMPREHENSIVE BENCHMARK FOR GENERATIVE VIDEO WORLD MODELS IN AUTONOMOUS DRIVING 69.53 University of Toronto, CUHK MMLab 自动驾驶 · 2026 90%
31 UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing 69.53 Harbin Institute of Technology, Harbin, China 图像恢复 · 2026 90%
32 Row-Column Separated Attention Based Low-Light Image/Video Enhancement 69.53 School of Artificial Intelligence, Jilin University, China; College of Software, Jilin University, China; Institute of Computing Technology, Chinese Academy of Sciences, China 图像增强 · 2026 90%
33 InTec: integrated things-edge computing A framework for distributing machine learning pipelines in edge AI systems 69.53 Faculty of Computer Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran; Big Data Research Center, Najafabad Branch, Islamic Azad University, Najafabad, Iran; School of Information Systems and Modelling, University of Technology Sydney, Ultimo, Sydney, NSW, Australia AI应用 · 2025 90%
34 SRU-Pix2Pix: A Fusion-Driven Generator Network for Medical Image Translation with Few-Shot Learning 69.53 School of Electronic and Electrical Engineering, Shanghai University of Engineering Science; Department of Thoracic Surgery, Zhongshan Hospital of Fudan University; Clinical Research Unit, Institute of Clinical Science, Zhongshan Hospital of Fudan University; Department of Medical Oncology, Cancer Center, and Fudan Zhangjiang Institute, Zhongshan Hospital of Fudan University AI医疗 · 2026 90%
35 SIMI: SELF-INFORMATION MINING NETWORK FOR LOW-LIGHT IMAGE ENHANCEMENT 69.53 Computer Vision Center, Barcelona, Spain; Computer Science Dept., Universitat Autonoma de Barcelona, Barcelona, Spain 图像增强 · 2026 90%
36 ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Driving 69.53 Intelligent Transportation Systems Research Center, Wuhan University of Technology; Department of Data and Systems Engineering, The University of Hong Kong; School of Computer Science and Artificial Intelligence, Wuhan University of Technology; School of Mechanical Engineering, Southeast University; School of Automotive Studies, Tongji University 未分类 · 2025 90%
37 PBE-UNet: A light weight Progressive Boundary-Enhanced U-Net with Scale-Aware Aggregation for Ultrasound Image Segmentation 69.53 Shaoxing University, Northeastern University, Chongqing University, Hangzhou City University, Zhejiang University, Information Technology R&D Innovation Center of Peking University AI医疗 · 2026 90%
38 Multi-stage image denoising with the wavelet transform 69.53 School of Software, Northwestern Polytechnical University, Xi’an, Shaanxi, 710129, China; National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, Xi’an, Shaanxi, 710129, China; School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, 150001; Peng Cheng Laboratory, Shenzhen, Guangdong, 518055, China; Department of Computer and Information Science, University of Macau, Macau, 999078, China; School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, 710129, China; School of Data Science, The Chinese University of Hong Kong (Shenzhen), Shenzhen, 518172, Guangdong, China; Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen, China 图像去噪 90%
39 BUSTR: BREAST ULTRASOUND TEXT REPORTING WITH A DESCRIPTOR-AWARE VISION–LANGUAGE MODEL 69.53 University of Nevada, Las Vegas AI医疗 · 2025 90%
40 Efficient Sequential Neural Network with Spatial-Temporal Attention and Linear LSTM for Robust Lane Detection Using Multi-Frame Images 69.53 Delft University of Technology 自动驾驶 · 2026 90%
41 MLFFM-SegDiff: A Multi-Level Feature Fusion Diffusion Model for Skin Lesion Segmentation 69.53 Keyi College of Zhejiang Sci-Tech University, Zhejiang Lanchen Digital Intelligence Technology Co., Ltd., Zhejiang University, Shanghai Academy of AI for Science, SAIS 图像分割 · 2026 90%
42 UNIR-Net: A Novel Approach for Restoring Underwater Images with Non-Uniform Illumination Using Synthetic Data 69.53 aSchool of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, 310018, Zhejiang, China bpannilrniedljevli00l 图像增强 · 2025 90%
43 Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks 69.53 Shenzhen University of Advanced Technology, Fudan University, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences 图像恢复 · 2026 90%
44 CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement 69.53 University of Science and Technology of China, Ant Group, University of Michigan - Ann Arbor, Sun Yat-sen University 图像恢复 · 2026 90%
45 HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation 69.53 Peking University, Harbin Institute of Technology, Shenzhen, Peng Cheng Laboratory 未分类 · 2025 90%
46 From Local Windows to Adaptive Candidates via Individualized Exploratory: Rethinking Attention for Image Super-Resolution 69.53 University of Electronic Science and Technology of China 图像恢复 · 2026 90%
47 ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models 69.53 Eastern Institute of Technology, Ningbo, Georgia Institute of Technology, Shanghai Jiao Tong University, Tsinghua University, University of Science and Technology of China, Peking University 视频生成 · 2026 90%
48 MedQ-UNI: Toward Unified Medical Image Quality Assessment and Restoration via Vision-Language Modeling 69.53 Fudan University, Shanghai, China; Shanghai Artificial Intelligence Laboratory, Shanghai, China AI医疗 · 2026 90%
49 OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution 69.53 ByteDance Inc., Peking University, The Chinese University of Hong Kong 图像恢复 · 2026 90%
50 STRUCTURED RAG FOR ANSWERING AGGREGATIVE QUESTIONS 69.53 AI21 Labs 大语言模型 · 2025 90%

排名用于发现值得进一步核查的论文，不替代同行评审。评分会随新增引用、复现、实验验证、新闻评价和落地证据持续更新。

社区反馈如何参与？

PaperMiner MCP已开放结构化论文反馈。可提交复现成功或失败、代码可运行或失效、Benchmark纠错、链接纠错和部署结果。

不直接改分反馈独立形成“社区信号”，与六维证据评分隔离。
必须带依据需要公开链接或实验结果哈希；无依据的点赞不进入系统。
自动交叉验证至少两个独立账号给出同类结论后，才标记为已有多人印证。
自动防刷个人密钥限频、去重；新账号和利益相关反馈自动降低权重。

MCP接口：submit_paper_feedback、get_paper_community_feedback

权限：有效PaperMiner账号获配的个人MCP密钥可提交；公共代理和共享只读密钥只能查询。每个账号每天最多提交5条新反馈。