{"total":50,"rows":[{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"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":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2603.12703","title":"SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance","created":"2026-03-13","cited_by_count":6,"area":null},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2603.24575","title":"VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models","created":"2026-03-25","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":"2603.18373","title":"To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2607.20785","title":"Robostral Navigate","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2604.00677","title":"CL-VISTA: Benchmarking Continual Learning in Video Large Language Models","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2607.26848","title":"ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching (ALD/E) Scientific Figures","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2602.10639","title":"VideoSTF: Stress-Testing Output Repetition in Video Large Language Models","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.12147","title":"EgoIntent: A Pre-Outcome Micro-Step Benchmark for Understanding What, Why, and Next","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.11038","title":"EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.21873","title":"Grounding Video Reasoning in Physical Signals","created":"2026-04-23","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":"2605.19075","title":"CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.21988","title":"Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.23826","title":"Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.03920","title":"Benchmarking Visual State Tracking in Multimodal Video Understanding","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.29531","title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","created":"2026-06-28","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":"2608.03160","title":"Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.23435","title":"Towards Comprehensive Basketball Understanding","created":"2026-08-24","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":"2608.30935","title":"LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.14080","title":"Adapting Open-Weight MLLMs to Generate Point Prompts for Electron Microscopy Segmentation","created":"2026-09-12","cited_by_count":1,"area":null},{"id":"2601.14121","title":"NewsRECON: News Article Retrieval for Image Contextualization","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.20354","title":"Leum-VL Technical Report","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.08522","title":"UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.13223","title":"Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.24291","title":"Rubato: Transcribing Piano Music with Timestamps","created":"2026-05-22","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":"2606.19096","title":"PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction","created":"2026-06-17","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":"2606.31876","title":"Harnessing Textual Refusal Directions for Multimodal Safety","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.12304","title":"What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.06361","title":"The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.18602","title":"Teach a Molmo2Fish: Towards interactive fish tracking with natural language guidance","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.23845","title":"Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.28192","title":"Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.10356","title":"Spot-the-shift: Evaluating Grounded Image Difference Captioning of Long-term Changes","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.18823","title":"Using OCR Heads to Verbalize Image Semantics","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.28467","title":"Where Should I Join? Robot Group Joining via Language-Guided Goal Prediction","created":"2026-09-23","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":"2609.33010","title":"Model-Aware Data Selection from In-and-Out Information Interplay","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35416","title":"When Should the Count Change? Learning State Maintenance for Causal Video Counting","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36875","title":"S4VY: Segment Anything in Feed-Forward 4D Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38155","title":"Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00451","title":"PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}