PAPER EVIDENCE RANKING
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。
| 排名 | 学校 | 得分 | 论文数 | 覆盖率 |
|---|---|---|---|---|
| 1 | 上海交通大学 Unsupervised Anomaly Detection in Brain MRI via Disentangled Anatomy Learning⋆ · LEIQ-Assessor: Multi-dimensional Quality Assessment of Low-light Enhanced Images via Multi-task Learning · Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language Models | 66.06 | 275 | 99% |
| 2 | Tsinghua University SpikACom: A Neuromorphic Computing Framework for Green Communications · LEGALONE: A FAMILY OF FOUNDATION MODELS FOR RELIABLE LEGAL REASONING · ScenePilot-Bench: A Large-Scale Dataset and Benchmark for Evaluation of Vision-Language Models in Autonomous Driving | 66.04 | 321 | 98% |
| 3 | Zhejiang University DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing · HGeo-TopoMap: Boosting Topological Mapping with Hierarchical Geometric Priors · RealHD: A High-Quality Dataset for Robust Detection of State-of-the-Art AI-Generated Images | 66.02 | 247 | 99% |
| 4 | Fudan University SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? · ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development · Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language Models | 65.7 | 154 | 96% |
| 5 | Peking University DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression · Crystal structure prediction with nuclear quantum and finite-temperature effects via deep free energy learning · VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding | 65.65 | 228 | 95% |
| 6 | The Chinese University of Hong Kong StyleDoctor: Towards Specialist Reward Model for Style-centric Generation Tasks · Approaching Low-Cost Cardiac Intelligence with Semi-Supervised Knowledge Distillation · FTDMamba: Frequency-Assisted Temporal Dilation Mamba for Unmanned Aerial Vehicle Video Anomaly Detection | 65.61 | 146 | 96% |
| 7 | National University of Singapore An Event-Based Opto-Tactile Skin · ALPaCA: Adapting Llama for Pathology Context Analysis to enable slide-level question answering · Certified Program Synthesis with a Multi-Modal Verifier | 65.41 | 148 | 98% |
| 8 | Stanford University The limits of fair medical imaging AI in real-world generalization · What LLMs Think When You Don’t Tell Them What to Think About? · CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models | 65.3 | 142 | 96% |
| 9 | University of Science and Technology of China DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing · Towards Expressive and Faithful Audio-to-Image Generation: A Unified Multimodal Dataset and Synthesis Framework · NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results | 65.28 | 183 | 95% |
| 10 | Massachusetts Institute of Technology The limits of fair medical imaging AI in real-world generalization · Deterministic access to global viral sequence data enables robust agent-driven scientific discovery · Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering | 65.24 | 138 | 95% |
| 11 | Wuhan University C2|Q⟩: A Robust Framework for Bridging Classical and Quantum Software Development — RCR Report · Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation · CoRE-UIR: Prior-guided common and residual experts for efficient all-in-one remote sensing image restoration | 65.15 | 78 | 96% |
| 12 | Nanjing University DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing · VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding · GAP-URGENET: A GENERATIVE-PREDICTIVE FUSION FRAMEWORK FOR UNIVERSAL SPEECH ENHANCEMENT | 64.97 | 89 | 94% |
| 13 | University College Causal-Adversarial Probing of Clinical Covariates for Prostate MRI Grading · INTRODUCTION AND NUMERICAL VALIDATION OF AN OPEN-SOURCE MATLAB PACKAGE FOR QUANTITATIVE ULTRASOUND TOMOGRAPHY VIA RAY-BORN INVERSION · A Foundational EDM2-Based Generative Model for High-Resolution Synthetic Fetal Ultrasound Imaging from Open Datasets | 64.89 | 80 | 96% |
| 14 | Sun Yat-sen University 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 · Comment Traps: How Defective Commented-out Code Augment Defects in AI-Assisted Code Generation | 64.86 | 77 | 94% |
| 15 | University of California Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering · ConvRML: High-Quality Lensless Imaging with Random Multi-Focal Lenslets · A Design Study on Voice-based Interaction for Immersive Network Visualization and Analysis | 64.79 | 223 | 96% |
| 16 | University of Chinese Academy of Sciences A Mutil-conditional Diffusion Transformer for Versatile Seismic Wave Generation · CL-VISTA: Benchmarking Continual Learning in Video Large Language Models · MGPC: Multimodal Network for Generalizable Point Cloud Completion With Modality Dropout and Progressive Decoding | 64.76 | 139 | 94% |
| 17 | Northwestern Polytechnical University Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset · SenFlow: Inter-Sentence Flow Modeling for AI-Generated Text Detection in Hybrid Documents · OODEval: Evaluating Large Language Models on Object-Oriented Design | 64.74 | 49 | 93% |
| 18 | University of Electronic Science and Technology of China Decoding the Sequence Determinants of Locus-Specific DNA Methylation Across Human Tissues · Spiking Variational Graph Representation Inference for Video Summarization · DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization | 64.72 | 67 | 95% |
| 19 | Harbin Institute of Technology High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection · Spiking Variational Graph Representation Inference for Video Summarization · UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing | 64.68 | 119 | 96% |
| 20 | University of Michigan Beyond Screenshots: Evaluating VLMs’ Understanding of UI Animations · EXP-Bench: Can AI Conduct AI Research Experiments? · On the Step Length Confounding in LLM Reasoning Data Selection | 64.66 | 75 | 94% |
| 21 | Nanyang Technological University VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding · Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs · R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment | 64.65 | 165 | 94% |
| 22 | Southeast University SpikACom: A Neuromorphic Computing Framework for Green Communications · OmniGAIA: Towards Native Omni-Modal AI Agents · Hybrid guided variational autoencoder for visual place recognition | 64.64 | 67 | 95% |
| 23 | The Hong Kong University of Science and Technology Metamorphic Testing for Audio Content Moderation Software · Relit-LiVE: Relight Video by Jointly Learning Environment Video · MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping | 64.63 | 162 | 94% |
| 24 | Beihang University ScenePilot-Bench: A Large-Scale Dataset and Benchmark for Evaluation of Vision-Language Models in Autonomous Driving · NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results · LLMs-Powered Accurate Extraction, Querying and Intelligent Management of Literature-derived 2D Materials Data | 64.58 | 84 | 94% |
| 25 | Technical University of Munich Coverage-Guided Road Selection and Prioritization for Efficient Testing in Autonomous Driving Systems · LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training · The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods for Federated Learning | 64.52 | 86 | 96% |
| 26 | The Hong Kong Polytechnic University NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results · RESTORATION ADAPTATION FOR SEMANTIC SEGMENTATION ON LOW QUALITY IMAGES · High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network | 64.51 | 66 | 92% |
| 27 | University of Pennsylvania A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration · A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration · DECIPHERING SCIENTIFIC COLLABORATION IN BIOMEDICAL LLM RESEARCH: DYNAMICS, INSTITUTIONAL PARTICIPATION, AND RESOURCE DISPARITIES | 64.48 | 52 | 93% |
| 28 | Huazhong University of Science and Technology High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network · WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects · Relit-LiVE: Relight Video by Jointly Learning Environment Video | 64.44 | 65 | 93% |
| 29 | Carnegie Mellon University CONCUR: BENCHMARKING LLMS FOR CONCURRENT CODEGENERATION · HOTPOTQA: A Dataset for Diverse, Explainable Multi-hop Question Answering · OMTRA: A Multi-Task Generative Model for Structure-Based Drug Design | 64.43 | 105 | 95% |
| 30 | City University of Hong Kong DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression · Approaching Low-Cost Cardiac Intelligence with Semi-Supervised Knowledge Distillation · Metamorphic Testing for Audio Content Moderation Software | 64.41 | 70 | 92% |
| 31 | 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 · ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Driving | 64.35 | 80 | 92% |
| 32 | Johns Hopkins University Transfer Learning from One Cancer to Another via Deep Learning Domain Adaptation · RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology · The Brain Resection Multimodal Image Registration (ReMIND2Reg) 2025 Challenge | 64.35 | 73 | 94% |
| 33 | 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 · Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis | 64.24 | 63 | 92% |
| 34 | 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 · ContractScrub: A benchmark for final review of legal contracts | 64.23 | 85 | 94% |
| 35 | Renmin University of China OmniGAIA: Towards Native Omni-Modal AI Agents · Metamorphic Testing for Audio Content Moderation Software · Feature Slice Matching for Precise Bug Detection | 64.12 | 44 | 93% |
| 36 | Xi’an Jiaotong University SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression · NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results · Universally Unfiltered and Unseen: Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards | 64.11 | 45 | 92% |
| 37 | Dalian University of Technology Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset · Revisiting Salient Object Detection from an Observer-Centric Perspective · DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion | 64.1 | 42 | 92% |
| 38 | New York University Solaris: Building a Multiplayer Video World Model in Minecraft · VTaMo: Video-Text Alignment Model for Sign Language Translation · EMBOMATRIX: A SCALABLE TRAINING-GROUND FOREMBODIED DECISION-MAKING | 64.06 | 85 | 96% |
| 39 | Tongji University An interactive enhanced driving dataset for autonomous driving · ScenePilot-Bench: A Large-Scale Dataset and Benchmark for Evaluation of Vision-Language Models in Autonomous Driving · ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Driving | 64.04 | 61 | 93% |
| 40 | Beijing University of Posts and Telecommunications SIDME: Self-supervised Image Demoiréing via Masked EncoderDecoder Reconstruction · Do Maps Still Matter for Machines: Revisiting the Role of Choropleth Maps in Foundation Model Spatial Understanding · Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Driving | 64.03 | 54 | 94% |
| 41 | Northeastern University NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results · Scaling up fine-grained intracranial vessel annotations in computed tomography angiography · From Noisy Historical Maps to Time-Series Oil Palm Mapping Without Annotation in Malaysia and Indonesia (2020–2024) | 64.01 | 69 | 94% |
| 42 | Nanjing University of Science and Technology AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results · The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · Decoupling Continual Semantic Segmentation | 63.97 | 44 | 92% |
| 43 | University of Washington Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstruction · LandmarkLens: Predicting and Presenting Efective Landmarks for Mixed-Reality Urban Exploration · The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report | 63.96 | 62 | 94% |
| 44 | 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 · T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability | 63.95 | 65 | 92% |
| 45 | University of Cambridge SurvSurf: a partially monotonic neural network for first-hitting time prediction of intermittently observed discrete and continuous sequential events · ALPaCA: Adapting Llama for Pathology Context Analysis to enable slide-level question answering · PMPBench: A Paired Multi-Modal Pan-Cancer Benchmark for Medical Image Synthesis | 63.87 | 88 | 94% |
| 46 | Indian Institute of Technology AUREXA-SE: Audio-Visual Unified Representation Exchange Architecture with Cross-Attention and Squeezeformer for Speech Enhancement · NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results · HiMed: Incentivizing Hindi Reasoning in Medical LLMs | 63.81 | 76 | 95% |
| 47 | Monash University High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection · PanopMamba: Vision State Space Modeling for Nuclei Panoptic Segmentation · Restormer: Efficient Transformer for High-Resolution Image Restoration | 63.81 | 48 | 92% |
| 48 | University of Oxford Connecting the Dots: A Machine Learning Ready Dataset for Ionospheric Forecasting Models · Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers · FDIF: Formula-Driven Supervised Learning with Implicit Functions for 3D Medical Image Segmentation | 63.75 | 84 | 93% |
| 49 | Cornell University Tracking and Understanding Object Transformations · The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report · Beyond Failure Recovery: An Engagement-Aware Human-in-the-loop Framework for Robotic Systems | 63.71 | 74 | 94% |
| 50 | Columbia University A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration · A Reproducible Evaluation of ANTs Similarity Metric Performance in Brain Image Registration · Visual Instruction Tuning | 63.66 | 59 | 94% |
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。
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。
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。