AAAI 2026 · 全部收录(123 篇)¶
仅列出通过预过滤且已打分的论文;分数是「评测方法学价值」,不是会议录用质量。 返回总览
| # | 论文 | 轨道 | 分数 | 链接 |
|---|---|---|---|---|
| 1 | Do Large Language Models Reason About Uncertainty Like Humans? A Benchmark on Hurricane Forecast Visualization Comprehension | Track 21 | 9 | 页 · PDF |
| 2 | ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction | Track 21 | 9 | 页 · PDF |
| 3 | ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction | Track 3 | 8 | 页 · PDF |
| 4 | BAG: Benchmarking Anomaly Detection on Dynamic Graphs | Track 17 | 8 | 页 · PDF |
| 5 | CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos | Track 8 | 8 | 页 · PDF |
| 6 | CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models | Track 8 | 8 | 页 · PDF |
| 7 | D-GARA: A Dynamic Benchmarking Framework for GUI Agent Robustness in Real-World Anomalies | Track 21 | 8 | 页 · PDF |
| 8 | Detecting Emotional Dynamic Trajectories: An Evaluation Framework for Emotional Support in Language Models | Track 3 | 8 | 页 · PDF |
| 9 | DISCODE: Distribution-Aware Score Decoder for Robust Automatic Evaluation of Image Captioning | Track 7 | 8 | 页 · PDF |
| 10 | EvalMuse-40K: A Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Alignment Evaluation | Track 6 | 8 | 页 · PDF |
| 11 | FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding | Track 10 | 8 | 页 · PDF |
| 12 | GEMA-Score: Granular Explainable Multi-Agent Scoring Framework for Radiology Report Evaluation | Track 15 | 8 | 页 · PDF |
| 13 | Inference Scaling Law for Retrieval Augmented Generation | Track 19 | 8 | 页 · PDF |
| 14 | JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics | Track 7 | 8 | 页 · PDF |
| 15 | LongT2IBench: A Benchmark for Evaluating Long Text-to-Image Generation with Graph-structured Annotations | Track 14 | 8 | 页 · PDF |
| 16 | Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Driving | Track 1 | 8 | 页 · PDF |
| 17 | MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction | Track 2 | 8 | 页 · PDF |
| 18 | Multigranular Evaluation for Brain Visual Decoding | Track 21 | 8 | 页 · PDF |
| 19 | NoReGeo: Non-Reasoning Geometry Benchmark | Track 23 | 8 | 页 · PDF |
| 20 | Rethinking Explanation Evaluation Under the Retraining Scheme | Track 24 | 8 | 页 · PDF |
| 21 | Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations | Track 5 | 8 | 页 · PDF |
| 22 | Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs | Track 14 | 8 | 页 · PDF |
| 23 | Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology | Track 22 | 8 | 页 · PDF |
| 24 | Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models | Track 4 | 8 | 页 · PDF |
| 25 | Who Is Helping Whom? Analyzing Inter-Dependencies to Evaluate Cooperation in Human-AI Teaming | Track 21 | 8 | 页 · PDF |
| 26 | Your AI-Generated Image Detector Can Secretly Achieve SOTA Accuracy, If Calibrated | Track 14 | 8 | 页 · PDF |
| 27 | AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning | Track 2 | 7 | 页 · PDF |
| 28 | AR-Nav Benchmark: Augmented Reality Navigation with Vision and Language | Track 21 | 7 | 页 · PDF |
| 29 | Benchmarking Visual LLMs Resilience to Unanswerable Questions on Visually Rich Documents | Track 10 | 7 | 页 · PDF |
| 30 | Beyond Counting: Evaluating Abstract and Emotional Reasoning in Vision-Language Models | Track 16 | 7 | 页 · PDF |
| 31 | CMedBench: A Comprehensive Benchmark for Efficient Medical Large Language Models | Track 25 | 7 | 页 · PDF |
| 32 | Complex Mathematical Expression Recognition: Benchmark, Large-Scale Dataset and Strong Baseline | Track 4 | 7 | 页 · PDF |
| 33 | DynamicEarth: How Far Are We from Open-Vocabulary Change Detection? | Track 8 | 7 | 页 · PDF |
| 34 | EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering | Track 8 | 7 | 页 · PDF |
| 35 | False Positives Matter: Multidimensional Localization Evaluation and Training-Free Explainable Adversarial Patch Defense | Track 7 | 7 | 页 · PDF |
| 36 | FIXME: Towards End-to-End Benchmarking of LLM-Aided Design Verification | Track 2 | 7 | 页 · PDF |
| 37 | Game Ground Bench: Probing the Limits of LVLMs in Complex Semantic Grounding Across Game Universes | Track 10 | 7 | 页 · PDF |
| 38 | GeoX-Bench: Benchmarking Cross-View Geo-Localization and Pose Estimation Capabilities of Large Multimodal Models | Track 16 | 7 | 页 · PDF |
| 39 | Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based Search | Track 21 | 7 | 页 · PDF |
| 40 | LLM-Free Image Captioning Evaluation in Reference-Flexible Settings | Track 6 | 7 | 页 · PDF |
| 41 | MDBench: Benchmarking Data-Driven Methods for Model Discovery | Track 24 | 7 | 页 · PDF |
| 42 | MIRA: Evaluating Multimodal AI on Complex Clinical Reasoning in Interventional Radiology | Track 8 | 7 | 页 · PDF |
| 43 | MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models | Track 11 | 7 | 页 · PDF |
| 44 | MosaicDoc: A Large-Scale Bilingual Benchmark for Visually Rich Document Understanding | Track 4 | 7 | 页 · PDF |
| 45 | OpenScan: A Benchmark for Generalized Open-Vocabulary 3D Scene Understanding | Track 16 | 7 | 页 · PDF |
| 46 | PEOD: A Pixel-Aligned Event-RGB Benchmark for Object Detection Under Challenging Conditions | Track 22 | 7 | 页 · PDF |
| 47 | Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric | Track 12 | 7 | 页 · PDF |
| 48 | ReFINE: A Reward-Based Framework for Interpretable and Nuanced Evaluation of Radiology Report Generation | Track 9 | 7 | 页 · PDF |
| 49 | scCluBench: Comprehensive Benchmarking of Clustering Algorithms for Single-Cell RNA Sequencing | Track 2 | 7 | 页 · PDF |
| 50 | SoMe: A Realistic Benchmark for LLM-based Social Media Agents | Track 2 | 7 | 页 · PDF |
| 51 | SpatialLogic-Bench: A Diagnostic Benchmark for Task-Oriented Spatiotemporal Reasoning | Track 23 | 7 | 页 · PDF |
| 52 | Textured Geometry Evaluation: Perceptual 3D Textured Shape Metric via 3D Latent-Geometry Network | Track 9 | 7 | 页 · PDF |
| 53 | Truth-Tracking Evaluation in Opinion-Based Argumentation | Track 23 | 7 | 页 · PDF |
| 54 | Unaligned UAV RGBT Tracking: A Largescale Benchmark and a Novel Approach | Track 13 | 7 | 页 · PDF |
| 55 | VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding | Track 6 | 7 | 页 · PDF |
| 56 | VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction | Track 12 | 7 | 页 · PDF |
| 57 | VisAssist: A Visually Impaired-Captured Video Question Answering Benchmark for Assistive Systems | Track 6 | 7 | 页 · PDF |
| 58 | VP-Bench: A Comprehensive Benchmark for Visual Prompting in Multimodal Large Language Models | Track 13 | 7 | 页 · PDF |
| 59 | Ψ-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback | Track 3 | 7 | 页 · PDF |
| 60 | An LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains | Track 2 | 6 | 页 · PDF |
| 61 | Benchmarking LLMs for Political Science: A United Nations Perspective | Track 1 | 6 | 页 · PDF |
| 62 | BREPS: Bounding-Box Robustness Evaluation of Promptable Segmentation | Track 10 | 6 | 页 · PDF |
| 63 | Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark | Track 16 | 6 | 页 · PDF |
| 64 | Fairness-Aware Design for Contextual Experiments: Guaranteeing Reliability and Equity in Heterogeneous Subgroups | Track 25 | 6 | 页 · PDF |
| 65 | FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation | Track 1 | 6 | 页 · PDF |
| 66 | GenVidBench: A 6-Million Benchmark for AI-Generated Video Detection | Track 18 | 6 | 页 · PDF |
| 67 | Griffin: Aerial-Ground Cooperative Detection and Tracking Dataset and Benchmark | Track 12 | 6 | 页 · PDF |
| 68 | Hi-EF: Benchmarking Emotion Forecasting in Human-interaction | Track 3 | 6 | 页 · PDF |
| 69 | Making Visual Dialogue More Engaging: A New Task, Method, and Metric | Track 19 | 6 | 页 · PDF |
| 70 | MODA: The First Challenging Benchmark for Multispectral Object Detection in Aerial Images | Track 6 | 6 | 页 · PDF |
| 71 | OTI: A Model-free and Visually Interpretable Measure of Image Attackability | Track 9 | 6 | 页 · PDF |
| 72 | Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation | Track 17 | 6 | 页 · PDF |
| 73 | RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis | Track 5 | 6 | 页 · PDF |
| 74 | Real Garment Benchmark (RGBench): A Comprehensive Benchmark for Robotic Garment Manipulation Featuring a High-Fidelity Scalable Simulator | Track 22 | 6 | 页 · PDF |
| 75 | RflyPano: A Panoramic Benchmark for Ultra-low Altitude UAV Localization Powered by RflySim | Track 22 | 6 | 页 · PDF |
| 76 | RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System | Track 6 | 6 | 页 · PDF |
| 77 | Segment Anything Across Shots: A Method and Benchmark | Track 6 | 6 | 页 · PDF |
| 78 | Semantic-Driven Visual Progressive Refinement for Aerial-Ground Person ReID: A Challenging Large-Scale Benchmark | Track 16 | 6 | 页 · PDF |
| 79 | Style4D-Bench: A Benchmark Suite for 4D Stylization | Track 4 | 6 | 页 · PDF |
| 80 | StyleDrive: Towards Driving-Style Aware Benchmarking of End-To-End Autonomous Driving | Track 6 | 6 | 页 · PDF |
| 81 | Thinking Aesthetics Assessment of Image Color Temperature: Models, Datasets and Benchmarks | Track 5 | 6 | 页 · PDF |
| 82 | TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs | Track 12 | 6 | 页 · PDF |
| 83 | TSBOW – Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions | Track 7 | 6 | 页 · PDF |
| 84 | UQ-Bench: A Benchmark for Evaluating Multimodal LLMs on Underwater Image Quality Assessment | Track 4 | 6 | 页 · PDF |
| 85 | VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation | Track 15 | 6 | 页 · PDF |
| 86 | AMS-IO-Bench and AMS-IO-Agent: Benchmarking and Structured Reasoning for Analog and Mixed-Signal Integrated Circuit Input/Output Design | Track 2 | 5 | 页 · PDF |
| 87 | Benchmarking Reinforcement Learning Algorithms for ICU Ventilator Settings: An Interpretable and Probabilistic Patient Environment for Doctor Agents | Track 24 | 5 | 页 · PDF |
| 88 | Burst Image Quality Assessment: A New Benchmark and Unified Framework for Multiple Downstream Tasks | Track 9 | 5 | 页 · PDF |
| 89 | DEGRE: Dynamic Gating Ensembles for Trust-Aware Rejection in Medical Image Diagnostics | Track 6 | 5 | 页 · PDF |
| 90 | Difficulty Controlled Diffusion Model for Synthesizing Effective Training Data | Track 12 | 5 | 页 · PDF |
| 91 | HDRMovieformer: A Transformer Framework and Benchmark for Cinematic SDR-to-HDR Conversion | Track 8 | 5 | 页 · PDF |
| 92 | HyperCOD: The First Challenging Benchmark and Baseline for Hyperspectral Camouflaged Object Detection | Track 4 | 5 | 页 · PDF |
| 93 | Learning Better UAV-Based Cross-View Object Geo-Localization from Multi-Modal Prompts: MoP-UAV Benchmark and MoPT Framework | Track 15 | 5 | 页 · PDF |
| 94 | LLMTM: Benchmarking and Optimizing LLMs for Temporal Motif Analysis in Dynamic Graphs | Track 17 | 5 | 页 · PDF |
| 95 | Multimodal Table Understanding with Difficulty-aware Reinforcement Learning | Track 1 | 5 | 页 · PDF |
| 96 | RIS-LAD: A Benchmark and Model for Referring Image Segmentation in Low-Altitude Drone Imagery | Track 14 | 5 | 页 · PDF |
| 97 | UVLM: Benchmarking Video Language Model for Underwater World Understanding | Track 14 | 5 | 页 · PDF |
| 98 | When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking | Track 8 | 5 | 页 · PDF |
| 99 | Context-aware Dynamic Contrastive Learning Network and E-Bike Rider Benchmark for Person Search | Track 8 | 4 | 页 · PDF |
| 100 | Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation | Track 18 | 4 | 页 · PDF |
| 101 | Intervention-Aware Time Series Modeling: Capturing and Evaluating Feature Dependencies | Track 25 | 4 | 页 · PDF |
| 102 | Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation | Track 17 | 4 | 页 · PDF |
| 103 | Pansharpening for Thin-Cloud Contaminated Remote Sensing Images: A Unified Framework and Benchmark Dataset | Track 5 | 4 | 页 · PDF |
| 104 | Veli: Unsupervised Method and Unified Benchmark for Low-Cost Air Quality Sensor Correction | Track 25 | 4 | 页 · PDF |
| 105 | When Person Re-Identification Meets Event Camera: A Benchmark Dataset and an Attribute-Guided Re-Identification Framework | Track 12 | 4 | 页 · PDF |
| 106 | CHIMERA: Controllable High-quality Image-Mask Extraction for Reliable Diffusion-based Anomaly Synthesis | Track 7 | 3 | 页 · PDF |
| 107 | Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection | Track 8 | 3 | 页 · PDF |
| 108 | FAMDR: Feature-Aligned Multimodal Denoising for Reliable Diagnostic Reconciliation in Medical Imaging | Track 9 | 3 | 页 · PDF |
| 109 | Noise-Aware Graph-Based Cognitive Diagnostic Framework Through Low-Rank Alignment | Track 19 | 3 | 页 · PDF |
| 110 | PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-Cancer | Track 1 | 3 | 页 · PDF |
| 111 | MACRec: A Multi-View Subspace Alignment Framework for Contrastive Sampling Calibration in Recommendation | Track 18 | 2 | 页 · PDF |
| 112 | Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size? | Track 24 | 2 | 页 · PDF |
| 113 | Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning | Track 10 | 2 | 页 · PDF |
| 114 | Temporal Calibrating and Distilling for Scene-Text Aware Text-Video Retrieval | Track 16 | 2 | 页 · PDF |
| 115 | AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization | Track 7 | 1 | 页 · PDF |
| 116 | Class Incremental Medical Image Segmentation via Prototype-Guided Calibration and Dual-Aligned Distillation | Track 16 | 1 | 页 · PDF |
| 117 | Escaping the CAM Shadow: Uncertainty-Guided Reliable Learning for Weakly Supervised Semantic Segmentation | Track 4 | 1 | 页 · PDF |
| 118 | MPI-Mamba: Latent Feature Fusion Mamba for Anisotropic Image Calibration and Deblurring in Magnetic Particle Imaging | Track 15 | 1 | 页 · PDF |
| 119 | MS-PPO: Mean Standard Deviation Proximal Policy Optimization for Reliable Parking Space Search in Structured Environments | Track 24 | 1 | 页 · PDF |
| 120 | RAC-DMVC: Reliability-Aware Contrastive Deep Multi-View Clustering Under Multi-Source Noise | Track 25 | 1 | 页 · PDF |
| 121 | RSOD: Reliability-Guided Sonar Image Object Detection with Extremely Limited Labels | Track 8 | 1 | 页 · PDF |
| 122 | SCAN: Self-Calibrated AutoregressioN for High-Quality Visual Generation | Track 5 | 1 | 页 · PDF |
| 123 | SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing | Track 12 | 1 | 页 · PDF |