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 | Stanford University Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank · The limits of fair medical imaging AI in real-world generalization · Embodied Referring Expression Comprehension in Human-Robot Interaction | 55.51 | 54 | 100% |
| 2 | Tsinghua University RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report · Post-Earthquake Restoration of Electricity-Gas Distribution Systems with Damage Information Collection and Repair Vehicle Routing · SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks | 55.2 | 84 | 100% |
| 3 | 上海交通大学 ICASSP 2026 URGENT SPEECH ENHANCEMENT CHALLENGE · 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 | 54.82 | 66 | 100% |
| 4 | Zhejiang University OmniPhys: Knowledge-Graph-Driven Benchmarking and Collective Optimization for Physical Commonsense in Text-to-Image Generation · RealHD: A High-Quality Dataset for Robust Detection of State-of-the-Art AI-Generated Images · PI2I: A Personalized Item-Based Collaborative Filtering Retrieval Framework | 54.7 | 61 | 100% |
| 5 | 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 · Two-magnon scattering in the framework of the Lippmann-Schwinger equation | 53.86 | 41 | 100% |
| 6 | Technical University of Munich What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under Browser Automation · LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training · Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models | 53.77 | 29 | 100% |
| 7 | Peking University FilDeep: Learning Large Deformations of Elastic-Plastic Solids with Multi-Fidelity Data · DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression · MMAE: A Massive Multitask Audio Editing Benchmark | 53.75 | 64 | 100% |
| 8 | Fudan University SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science? · ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development · RIVER: A REAL-TIME INTERACTION BENCHMARK FOR VIDEO LLMS | 53.75 | 41 | 100% |
| 9 | University of Science and Technology of China NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results · Towards Expressive and Faithful Audio-to-Image Generation: A Unified Multimodal Dataset and Synthesis Framework · RIVER: A REAL-TIME INTERACTION BENCHMARK FOR VIDEO LLMS | 53.73 | 50 | 100% |
| 10 | The Chinese University of Hong Kong StyleDoctor: Towards Specialist Reward Model for Style-centric Generation Tasks · CA-DEL: An Open Multi-Target, Multi-Modal Benchmark for Learning from DNA-Encoded Library Screens · SUMMARY OF THE INAUGURAL MUSIC SOURCE RESTORATION CHALLENGE | 53.67 | 31 | 100% |
| 11 | University of Trento Feature Slice Matching for Precise Bug Detection · The bliss of dimensionality: how an unsupervised criterion identifies optimal low-resolution representations of high-dimensional datasets · Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior | 53.64 | 10 | 100% |
| 12 | Hefei University of Technology RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report · MVAD : A Comprehensive Multimodal Video-Audio Dataset for AIGC Detection · Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report | 53.6 | 10 | 100% |
| 13 | Northeastern University RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report · NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results · SVD: Spatial Video Dataset | 53.55 | 19 | 100% |
| 14 | University of California 3D-DefectBench: A Controlled Factorial Study of Vision-Language Model Evaluation Pipelines for Fine-Grained 3D Generation Defects · ConvRML: High-Quality Lensless Imaging with Random Multi-Focal Lenslets · Predicting food taste with bound-driven optimization | 53.51 | 58 | 100% |
| 15 | National University of Singapore DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection · Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation · Talk2AI: A Longitudinal Dataset of Human–AI Persuasive Conversations | 53.47 | 44 | 100% |
| 16 | Tongji University RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report · 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 | 53.4 | 10 | 100% |
| 17 | King’s College A Foundational EDM2-Based Generative Model for High-Resolution Synthetic Fetal Ultrasound Imaging from Open Datasets · SUMMARY OF THE INAUGURAL MUSIC SOURCE RESTORATION CHALLENGE · RESOLUTION INVARIANT AUTOENCODER | 53.4 | 10 | 100% |
| 18 | Wuhan University C2|Q⟩: A Robust Framework for Bridging Classical and Quantum Software Development — RCR Report · Towards Visual Query Localization in the 3D World · ActiveFreq: Integrating Active Learning and Frequency Domain Analysis for Interactive Segmentation | 53.37 | 23 | 100% |
| 19 | University of Chinese Academy of Sciences Discovery and Characterization of White Dwarf–FGK Main-sequence Binaries within the Optical Main-sequence Locus · Towards Visual Query Localization in the 3D World · A Mutil-conditional Diffusion Transformer for Versatile Seismic Wave Generation | 53.21 | 28 | 100% |
| 20 | University College Causal-Adversarial Probing of Clinical Covariates for Prostate MRI Grading · A Foundational EDM2-Based Generative Model for High-Resolution Synthetic Fetal Ultrasound Imaging from Open Datasets · Oxygen K-edge X-ray Absorption Spectroscopy Database for NMC811 Layered Cathode Materials | 53.19 | 28 | 100% |
| 21 | City University of Hong Kong DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression · An Underwater Image Enhancement Benchmark Dataset and Beyond · Approaching Low-Cost Cardiac Intelligence with Semi-Supervised Knowledge Distillation | 53.03 | 17 | 100% |
| 22 | Tianjin University RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report · Decoding the Sequence Determinants of Locus-Specific DNA Methylation Across Human Tissues · An Underwater Image Enhancement Benchmark Dataset and Beyond | 53.02 | 12 | 100% |
| 23 | Johns Hopkins University On-Detector Machine Learning for Beam-Induced Background Rejection at a 10 TeV Muon Collider · RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology · SUMMARY OF THE INAUGURAL MUSIC SOURCE RESTORATION CHALLENGE | 53.01 | 23 | 100% |
| 24 | Beijing University of Posts and Telecommunications Do Maps Still Matter for Machines: Revisiting the Role of Choropleth Maps in Foundation Model Spatial Understanding · An Attention-Enhanced $\Phi$ -OTDR Event Recognition Framework for Edge-Based Distributed Acoustic Sensing · CORE: Toward Ubiquitous 6G Intelligence Through Collaborative Orchestration of Large Language Model Agents Over Hierarchical Edge | 52.92 | 16 | 100% |
| 25 | The Hong Kong University of Science and Technology An Attention-Enhanced $\Phi$ -OTDR Event Recognition Framework for Edge-Based Distributed Acoustic Sensing · Metamorphic Testing for Audio Content Moderation Software · A Dual-Band Reconfigurable Shared-Aperture Antenna Array With Independent Sub-6-GHz and Centimeter-Wave Beam Control | 52.9 | 39 | 100% |
| 26 | 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 | 52.9 | 32 | 100% |
| 27 | 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 · High-speed and High-quality Vision Reconstruction of Spike Camera with Spike Stability Theorem | 52.87 | 17 | 96% |
| 28 | The Hong Kong Polytechnic University Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report · NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results · RESTORATION ADAPTATION FOR SEMANTIC SEGMENTATION ON LOW QUALITY IMAGES | 52.86 | 14 | 100% |
| 29 | University of Wurzburg RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report · Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report · NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results | 52.84 | 12 | 100% |
| 30 | Lomonosov Moscow State University NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results · EXPLORING REAL-TIME SUPER-RESOLUTION: BENCHMARKING AND FINE-TUNING FOR STREAMING CONTENT · MGRegBench: A Novel Benchmark Dataset with Anatomical Landmarks for Mammography Image Registration | 52.77 | 11 | 100% |
| 31 | University of Pennsylvania When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals · 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 | 52.75 | 16 | 100% |
| 32 | University of Illinois Urbana-Champaign CLIMB: Data Foundations for Large Scale Multimodal Clinical Foundation Models · Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation · Investigating the Presence and Development of Student Instructor Preferences in a Large-Scale CS1 Course | 52.68 | 13 | 100% |
| 33 | Nanjing University Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report · VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding · RIVER: A REAL-TIME INTERACTION BENCHMARK FOR VIDEO LLMS | 52.65 | 19 | 100% |
| 34 | University of Edinburgh What do student responses to the car-truck problems tell us? An investigation into two Force Concept Inventory questions · Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yoruba · Single Pixel Image Classification using an Ultrafast Digital Light Projector | 52.56 | 13 | 100% |
| 35 | Indian Institute of Technology AUREXA-SE: Audio-Visual Unified Representation Exchange Architecture with Cross-Attention and Squeezeformer for Speech Enhancement · Federated Graph AGI for Cross-Border Insider Threat Intelligence in Government Financial Schemes · Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report | 52.53 | 26 | 100% |
| 36 | Nanyang Technological University VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding · R4-CGQA: Retrieval-based Vision Language Models for Computer Graphics Image Quality Assessment · Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs | 52.5 | 29 | 100% |
| 37 | Texas A&M University NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results · Evaluating GAN-LSTM for Smart Meter Anomaly Detection in Power Systems · CONCUR: BENCHMARKING LLMS FOR CONCURRENT CODEGENERATION | 52.5 | 12 | 100% |
| 38 | Harbin Institute of Technology RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report · High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection · FiRE \ : Enhancing MLLMs with Fine-Grained Context Learning for Complex Image Retrieval | 52.49 | 23 | 100% |
| 39 | Northwestern University PPDM: Pixel Puzzling Diffusion Model for Speed and Memory Efficient Volumetric Medical Image Translation · Localizing RL-Induced Tool Use to a Single Crosscoder Feature · On-Detector Machine Learning for Beam-Induced Background Rejection at a 10 TeV Muon Collider | 52.46 | 11 | 100% |
| 40 | University of Michigan Bi3: A Biplatform, Bicultural, Biperson Dataset for Social Robot Navigation · On the Step Length Confounding in LLM Reasoning Data Selection · Beyond Screenshots: Evaluating VLMs’ Understanding of UI Animations | 52.36 | 25 | 100% |
| 41 | Monash University What Does a Software Engineer Look Like? Exploring Societal Stereotypes in LLMs · High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection · People-Centred Medical Image Analysis | 52.36 | 15 | 100% |
| 42 | Renmin University of China Feature Slice Matching for Precise Bug Detection · OmniGAIA: Towards Native Omni-Modal AI Agents · Metamorphic Testing for Audio Content Moderation Software | 52.29 | 12 | 100% |
| 43 | 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 · Structure-Aware Multimodal LLM Framework for Trustworthy Near-Field Beam Prediction | 52.27 | 22 | 100% |
| 44 | Yale University LitBench: A Graph-Centric Large Language Model Benchmarking Tool For Literature Tasks · PPDM: Pixel Puzzling Diffusion Model for Speed and Memory Efficient Volumetric Medical Image Translation · A Speech-to-Video Synthesis Approach Using Spatio-Temporal Diffusion for Vocal Tract MRI | 52.26 | 24 | 100% |
| 45 | Nanjing University of Science and Technology LoBoFit: Flexible Garment Refitting via Local Bone Mapping Blending · Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report · LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results | 52.15 | 11 | 100% |
| 46 | Xidian University RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report · DSPE: An Energy-Efficient Edge Processor for DeepSeek Inference with MerkleTree-based Incremental Pruning, Multi-Stage Boothing Lookup and Dynamic Adaptive Posit Processing · Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report | 52.09 | 11 | 100% |
| 47 | University of Electronic Science and Technology of China Decoding the Sequence Determinants of Locus-Specific DNA Methylation Across Human Tissues · Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis · Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report | 52.06 | 20 | 100% |
| 48 | Cornell University On-Detector Machine Learning for Beam-Induced Background Rejection at a 10 TeV Muon Collider · CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoising · Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioning | 52.04 | 32 | 100% |
| 49 | Vanderbilt University Liberals are less willing to buy Teslas than other electric vehicles, moderated by perceptions of Elon Musk · A Reinforcement Learning Approach to Synthetic Data Generation · DECIPHERING SCIENTIFIC COLLABORATION IN BIOMEDICAL LLM RESEARCH: DYNAMICS, INSTITUTIONAL PARTICIPATION, AND RESOURCE DISPARITIES | 51.99 | 18 | 100% |
| 50 | Seoul National University Probabilistic denoising for reliable signal extraction in spectroscopy · Sequential Testing for Descriptor-Agnostic LiDAR Loop Closure in Repetitive Environments · The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods for Federated Learning | 51.94 | 15 | 100% |
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。