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% 至少3篇论文，取Top 20均值并校正样本量
排名 学校 得分 论文数 覆盖率
1 Tsinghua University ScenePilot-Bench: A Large-Scale Dataset and Benchmark for Evaluation of Vision-Language Models in Autonomous Driving · OmniGAIA: Towards Native Omni-Modal AI Agents · NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results 74.75 321 100%
2 上海交通大学 Towards Visual Query Localization in the 3D World · NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results · Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies 74.75 274 100%
3 Zhejiang University RealHD: A High-Quality Dataset for Robust Detection of State-of-the-Art AI-Generated Images · NeurIDA: Dynamic Modeling for Effective In-Database Analytics · OmniGAIA: Towards Native Omni-Modal AI Agents 74.75 246 100%
4 Peking University Efficient Content-based Recommendation Model Training via Noise-aware Coreset Selection · Crystal structure prediction with nuclear quantum and finite-temperature effects via deep free energy learning · FilDeep: Learning Large Deformations of Elastic-Plastic Solids with Multi-Fidelity Data 74.75 227 100%
5 University of California L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery · ConvRML: High-Quality Lensless Imaging with Random Multi-Focal Lenslets · Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering 74.75 223 100%
6 University of Science and Technology of China RIVER: A REAL-TIME INTERACTION BENCHMARK FOR VIDEO LLMS · NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results · The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report 74.75 183 100%
7 Nanyang Technological University NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results · RecNextEval: A Reference Implementation for Temporal Next-Batch Recommendation Evaluation · R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment 74.75 165 95%
8 The Hong Kong University of Science and Technology Enhancing AIGC Service Efficiency with Adaptive Multi-Edge Collaboration in A Distributed System · LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation · Relit-LiVE: Relight Video by Jointly Learning Environment Video 74.75 162 96%
9 Fudan University ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development · RIVER: A REAL-TIME INTERACTION BENCHMARK FOR VIDEO LLMS · FCMBench-Video: A Benchmark for Document-Video Intelligence 74.75 154 100%
10 National University of Singapore Factorized Learning for Temporally Grounded Video-Language Models · NeurIDA: Dynamic Modeling for Effective In-Database Analytics · NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results 74.75 147 100%
11 The Chinese University of Hong Kong Approaching Low-Cost Cardiac Intelligence with Semi-Supervised Knowledge Distillation · ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis · Relit-LiVE: Relight Video by Jointly Learning Environment Video 74.75 145 98%
12 Stanford University CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models · The limits of fair medical imaging AI in real-world generalization · What LLMs Think When You Don’t Tell Them What to Think About? 74.75 142 98%
13 University of Chinese Academy of Sciences Towards Visual Query Localization in the 3D World · A Mutil-conditional Diffusion Transformer for Versatile Seismic Wave Generation · Relit-LiVE: Relight Video by Jointly Learning Environment Video 74.75 139 94%
14 Massachusetts Institute of Technology Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies · The limits of fair medical imaging AI in real-world generalization · Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering 74.75 138 97%
15 Harbin Institute of Technology High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection · NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results · Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering 74.75 119 96%
16 Carnegie Mellon University CONCUR: BENCHMARKING LLMS FOR CONCURRENT CODEGENERATION · LLM-based Multimodal Feedback Produces Equivalent Learning and Better Student Perceptions than Educator Feedback · HOTPOTQA: A Dataset for Diverse, Explainable Multi-hop Question Answering 74.75 105 95%
17 Nanjing University RIVER: A REAL-TIME INTERACTION BENCHMARK FOR VIDEO LLMS · The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · GAP-URGENET: A GENERATIVE-PREDICTIVE FUSION FRAMEWORK FOR UNIVERSAL SPEECH ENHANCEMENT 74.75 89 95%
18 University of Cambridge PMPBench: A Paired Multi-Modal Pan-Cancer Benchmark for Medical Image Synthesis · SurvSurf: a partially monotonic neural network for first-hitting time prediction of intermittently observed discrete and continuous sequential events · Iterative AI-guided optimisation of selective triple-drug combinations for breast cancer 74.75 88 94%
19 Technical University of Munich VariViT: A Vision Transformer for Variable Image Sizes · MT4G: A Tool for Reliable Auto-Discovery of NVIDIA and AMD GPU Compute and Memory Topologies · MedSEBA: Synthesizing Evidence-Based Answers Grounded in Evolving Medical Literature 74.75 86 96%
20 New York University Solaris: Building a Multiplayer Video World Model in Minecraft · Interactive Data Harmonization with LLM Agents: Opportunities and Challenges · Generative Recursive Reasoning 74.75 85 96%
21 Imperial College SpikACom: A Neuromorphic Computing Framework for Green Communications · The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods for Federated Learning · GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models 74.75 85 95%
22 Beihang University ScenePilot-Bench: A Large-Scale Dataset and Benchmark for Evaluation of Vision-Language Models in Autonomous Driving · NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results · LLMs-Powered Accurate Extraction, Querying and Intelligent Management of Literature-derived 2D Materials Data 74.75 84 94%
23 University of Oxford Connecting the Dots: A Machine Learning Ready Dataset for Ionospheric Forecasting Models · GMOS: Grounding Moving Object Segmentation in 3D Space and Time · Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering 74.75 84 93%
24 University College Compositional Segmentation of Cardiac Images Leveraging Metadata · Zero-shot Monocular Metric Depth for Endoscopic Images · INTRODUCTION AND NUMERICAL VALIDATION OF AN OPEN-SOURCE MATLAB PACKAGE FOR QUANTITATIVE ULTRASOUND TOMOGRAPHY VIA RAY-BORN INVERSION 74.75 80 96%
25 The University of Hong Kong MatTools: Benchmarking Large Language Models for Materials Science Tools · LLM-based Multimodal Feedback Produces Equivalent Learning and Better Student Perceptions than Educator Feedback · Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation 74.75 80 93%
26 Wuhan University Towards Visual Query Localization in the 3D World · Universally Unfiltered and Unseen: Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards · Continual Vision-Language Learning for Remote Sensing: Benchmarking and Analysis 74.75 78 96%
27 Sun Yat-sen University NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results · DepthAnything and SAM for UIE: Exploring Large Model Information Contributes to Underwater Image Restoration · DepthAnything and SAM for UIE: Exploring Large Model Information Contributes to Underwater Image Restoration 74.75 76 94%
28 University of Michigan L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery · Bi3: A Biplatform, Bicultural, Biperson Dataset for Social Robot Navigation · PRIVATEEDIT: A Privacy-Preserving Pipeline for Face-Centric Generative Image Editing 74.75 75 94%
29 Cornell University The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · Tracking and Understanding Object Transformations · Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking 74.75 74 94%
30 Johns Hopkins University RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology · SUMMARY OF THE INAUGURAL MUSIC SOURCE RESTORATION CHALLENGE · Large Variations Seen in First Ultraviolet Spectroscopic M33 Dust Extinction Curves 74.75 73 95%
31 University of Toronto LoRAFusion: Efficient LoRA Fine-Tuning for LLMs · Reasoning About Reasoning: Towards Informed and Reflective Use of LLM Reasoning in HCI · Velox: Learning Representations of 4D Geometry and Appearance 74.75 70 94%
32 City University of Hong Kong Approaching Low-Cost Cardiac Intelligence with Semi-Supervised Knowledge Distillation · Metamorphic Testing for Audio Content Moderation Software · DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression 74.75 70 92%
33 Northeastern University The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · From Noisy Historical Maps to Time-Series Oil Palm Mapping Without Annotation in Malaysia and Indonesia (2020–2024) · NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results 74.75 69 93%
34 Southeast University OmniGAIA: Towards Native Omni-Modal AI Agents · V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative Views · Dependency-Guided Repository-Level C-to-Rust Translation with Reinforcement Alignment 74.75 67 96%
35 University of Electronic Science and Technology of China DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization · The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results 74.75 67 95%
36 The Hong Kong Polytechnic University High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network · The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · RESTORATION ADAPTATION FOR SEMANTIC SEGMENTATION ON LOW QUALITY IMAGES 74.75 66 93%
37 Huazhong University of Science and Technology High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network · Source-Free Domain Adaptation (SFDA) for Privacy-Preserving Seizure Subtype Classification · Relit-LiVE: Relight Video by Jointly Learning Environment Video 74.75 65 94%
38 University of Illinois Urbana-Champaign CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models · NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results · Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection 74.75 65 92%
39 Beijing Institute of Technology Data Science and Technology Towards AGI Part I: Tiered Data Management · MM-DETR: An Efficient Multimodal Detection Transformer with Mamba-Driven Dual-Granularity Fusion and Frequency-Aware Modality Adapters · Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation 74.75 63 92%
40 University of Washington The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction · Predicting Poets’ Origins from Verse: A Computational Analysis of Regional Linguistic Fingerprints in the Complete Tang Poems 74.75 62 94%
41 University of Pennsylvania DECIPHERING SCIENTIFIC COLLABORATION IN BIOMEDICAL LLM RESEARCH: DYNAMICS, INSTITUTIONAL PARTICIPATION, AND RESOURCE DISPARITIES · A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration · The Brain Resection Multimodal Image Registration (ReMIND2Reg) 2025 Challenge 74.75 52 94%
42 Northwestern Polytechnical University A Generative Data Framework with Authentic Supervision for Underwater Image Restoration and Enhancement · Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset · OODEval: Evaluating Large Language Models on Object-Oriented Design 74.75 49 93%
43 Monash University Human Factors in Immersive Analytics · High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection · Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering 74.75 48 92%
44 Xi’an Jiaotong University Universally Unfiltered and Unseen: Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards · NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results · NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results 74.75 45 92%
45 Renmin University of China OmniGAIA: Towards Native Omni-Modal AI Agents · Graph Retrieval-Augmented Generation: A Survey · Metamorphic Testing for Audio Content Moderation Software 74.75 44 94%
46 Nanjing University of Science and Technology NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results · The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results 74.75 44 92%
47 Dalian University of Technology The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset · Revisiting Salient Object Detection from an Observer-Centric Perspective 74.75 42 92%
48 Tongji University ScenePilot-Bench: A Large-Scale Dataset and Benchmark for Evaluation of Vision-Language Models in Autonomous Driving · An interactive enhanced driving dataset for autonomous driving · MAP: End-to-End Autonomous Driving with Map-Assisted Planning 73.4 61 93%
49 Columbia University Visual Instruction Tuning · A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration · A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration 73.4 59 94%
50 Purdue University PRIVATEEDIT: A Privacy-Preserving Pipeline for Face-Centric Generative Image Editing · FathomGPT: A Natural Language Interface for Interactively Exploring Ocean Science Data · Let’s Ask Gauss: Improved One-Run Privacy Auditing 73.4 57 93%

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。