{"total":69,"rows":[{"id":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2512.04451","title":"StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2602.16110","title":"OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis","created":"2026-02-18","cited_by_count":10,"area":null},{"id":"2607.14935","title":"VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding","created":"2026-07-16","cited_by_count":10,"area":null},{"id":"2512.17495","title":"GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation","created":"2025-12-19","cited_by_count":9,"area":null},{"id":"2602.04279","title":"ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation","created":"2026-02-04","cited_by_count":9,"area":null},{"id":"2603.20422","title":"PEARL: Personalized Streaming Video Understanding Model","created":"2026-03-20","cited_by_count":9,"area":null},{"id":"2512.03575","title":"UniComp: Rethinking Video Compression Through Informational Uniqueness","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2602.11506","title":"RooflineBench: A Benchmarking Framework for On-Device LLMs via Roofline Analysis","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2605.10343","title":"EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2605.11960","title":"Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters","created":"2026-05-12","cited_by_count":5,"area":null},{"id":"2607.13639","title":"OvisOCR2 Technical Report","created":"2026-07-15","cited_by_count":5,"area":null},{"id":"2509.18588","title":"UniECG: Understanding and Generating ECG in One Unified Model","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2512.14870","title":"HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2605.07492","title":"How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2605.10079","title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2605.18984","title":"Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2601.04350","title":"RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2603.14686","title":"MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2605.20035","title":"Stage-adaptive Token Selection for Efficient Omni-modal LLMs","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2603.15409","title":"SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2606.01348","title":"ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2608.20958","title":"TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming","created":"2026-08-21","cited_by_count":2,"area":null},{"id":"2603.17554","title":"Prompt-Free Universal Region Proposal Network","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2603.24078","title":"PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2605.02782","title":"When Audio-Language Models Fail to Leverage Multimodal Context for Dysarthric Speech Recognition","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.05955","title":"TableVista: Benchmarking Multimodal Table Reasoning under Visual and Structural Complexity","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.07593","title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.14664","title":"MiVE: Multiscale Vision-language features for reference-guided video Editing","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.31351","title":"VIABLE: A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.30026","title":"MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.01117","title":"MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.21061","title":"MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2607.24077","title":"When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2607.27895","title":"MMHBench: A Multi-Perspective Benchmark for Mental Health Understanding in Long-Form Videos","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.09573","title":"VideoVIBE: A Video-Grounded Diagnostic Benchmark for One-Shot Interactive Website Generation","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.21244","title":"A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2608.26517","title":"HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2601.00150","title":"FCMBench: The First Large-scale Financial Credit Multimodal Benchmark for Real-world Applications","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2603.17761","title":"Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2605.19522","title":"iDiff: Interpretable Difference-aware Framework for Pairwise Image Quality Assessment","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.21411","title":"RoadTones: Tone Controllable Text Generation from Road Event Videos","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.25706","title":"Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.02482","title":"X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.03635","title":"VidMsg: A Benchmark for Implicit Message Inference in Short Videos","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.16601","title":"DifferAD-R1: A Difference-Guided IndustrialAnomaly Localization with Multimodal LargeLanguage Models","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.19100","title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.14660","title":"VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.16243","title":"RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.23870","title":"MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.05825","title":"MoCA: Implicit Social Context Analysis","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.11692","title":"HUGIN: Enhancing Vision-Language Planning for Autonomous Logistics Sorting","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.19297","title":"Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.21360","title":"OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.25559","title":"AdaVDR: Adaptive Tool Use and Reflection for Video Deep Research","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.28630","title":"Enabling Proactive Spoken Turns via a Generalized Style-Aware Full-Duplex Framework","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.29865","title":"ManGo: Manga Active Narrative Grounding Optimization","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.04242","title":"Training-Free Speech-Centric Omni Understanding with Frozen VLMs","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.08657","title":"Charts Are Beyond Pixels: Probing for Layer-Wise Chart Understanding and Editing","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.20423","title":"WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.20508","title":"Grounded Product Understanding in Livestream Videos","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.23592","title":"Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.24092","title":"DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.30981","title":"STORM-Bench: Evaluating Online Video QA under Evolving and Incomplete Evidence","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.08162","title":"The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.17731","title":"Understanding Machine Taste: Aesthetic Agreement Across Foundation Models in K-pop","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.17991","title":"PolUR: Polarization Aware Multimodal Degradation Perception for Underwater Image Restoration","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}