{"total":64,"rows":[{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824,"area":null},{"id":"2503.13436","title":"Unified Autoregressive Visual Generation and Understanding with Continuous Tokens","created":"2025-03-17","cited_by_count":51,"area":null},{"id":"2505.23189","title":"TrackVLA: Embodied Visual Tracking in the Wild","created":"2025-05-29","cited_by_count":47,"area":null},{"id":"2505.07813","title":"DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies","created":"2025-05-12","cited_by_count":38,"area":null},{"id":"2509.25134","title":"LayerD: Decomposing Raster Graphic Designs into Layers","created":"2025-09-29","cited_by_count":21,"area":null},{"id":"2512.14856","title":"T5Gemma 2: Seeing, Reading, and Understanding Longer","created":"2025-12-16","cited_by_count":17,"area":null},{"id":"2504.05400","title":"GARF: Learning Generalizable 3D Reassembly for Real-World Fractures","created":"2025-04-07","cited_by_count":13,"area":null},{"id":"2502.16612","title":"MemeIntel: Explainable Detection of Propagandistic and Hateful Memes","created":"2025-02-23","cited_by_count":10,"area":null},{"id":"2502.19335","title":"Gatekeeper: Improving Model Cascades Through Confidence Tuning","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2503.07920","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2504.15707","title":"RePOPE: Impact of Annotation Errors on the POPE Benchmark","created":"2025-04-22","cited_by_count":9,"area":null},{"id":"2502.14780","title":"ReVision: A Dataset and Baseline VLM for Privacy-Preserving Task-Oriented Visual Instruction Rewriting","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2601.02457","title":"PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding","created":"2026-01-05","cited_by_count":6,"area":null},{"id":"2506.07015","title":"TABLET: Table Structure Recognition using Encoder-only Transformers","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2506.18267","title":"ARD-LoRA: Dynamic Rank Allocation for Parameter-Efficient Fine-Tuning of Foundation Models with Heterogeneous Adaptation Needs","created":"2025-06-23","cited_by_count":5,"area":null},{"id":"2506.06205","title":"Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2509.25339","title":"VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2604.10787","title":"When Meaning Isn't Literal: Exploring Idiomatic Meaning Across Languages and Modalities","created":"2026-04-12","cited_by_count":4,"area":null},{"id":"2605.10761","title":"RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2506.22967","title":"ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2508.21052","title":"FakeParts: a New Family of AI-Generated DeepFakes","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2512.15098","title":"Uni-Parser Technical Report","created":"2025-12-17","cited_by_count":3,"area":null},{"id":"2412.12740","title":"Open-World Panoptic Segmentation","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2506.04822","title":"Evaluating Vision-Language and Large Language Models for Automated Student Assessment in Indonesian Classrooms","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2511.17411","title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2511.21982","title":"DialBench: Towards Accurate Reading Recognition of Pointer Meter using Large Foundation Models","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2512.10888","title":"PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2603.28550","title":"MarkushGrapher-2: End-to-end Multimodal Recognition of Chemical Structures","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2606.25206","title":"RAVEN: Long-Horizon Reasoning & Navigation with a Visuo-Spatio-Temporal Memory","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2505.15050","title":"Entailed Opinion Matters: Improving the Fact-Checking Performance of Language Models by Relying on their Entailment Ability","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.24211","title":"Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2510.08278","title":"A Multimodal Depth-Aware Method For Embodied Reference Understanding","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2511.14229","title":"EBind: a practical approach to space binding","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2511.19470","title":"Quantifying Modality Contributions via Disentangling Multimodal Representations","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2601.06458","title":"PixRec: Leveraging Visual Context for Next-Item Prediction in Sequential Recommendation","created":"2026-01-10","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":"2605.22255","title":"Direct content-based retrieval from music scores images","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.09479","title":"Optical Music Recognition for Real-World Manuscripts with Synthetic Data","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.14772","title":"ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2505.23078","title":"Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2507.21888","title":"CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2508.16527","title":"Towards Open World Detection: A Survey","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2509.15211","title":"What's the Best Way to Retrieve Slides? A Comparative Study of Multimodal, Caption-Based, and Hybrid Retrieval Techniques","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.02922","title":"Multimodal Carotid Risk Stratification with Large Vision-Language Models: Benchmarking, Fine-Tuning, and Clinical Insights","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2512.18004","title":"Seeing Justice Clearly: Handwritten Legal Document Translation with OCR and Vision-Language Models","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2603.13571","title":"DiveUp: Learning Feature Upsampling from Diverse Vision Foundation Models","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.27033","title":"RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2603.28363","title":"SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2603.29422","title":"Multimodal Models Meet Presentation Attack Detection on ID Documents","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.03953","title":"Multimodal Structure Learning: Disentangling Shared and Specific Topology via Cross-Modal Graphical Lasso","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2606.00145","title":"Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.15241","title":"Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.22877","title":"Towards Trustworthy Physical Intelligence: From Theory to Practice Across Life Cycle","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.04554","title":"Representing Visual Evidence for Item Difficulty Prediction: Visual Textualization and Image-Native Modeling","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.20069","title":"V-REX: Efficient Specialist VLM Training for Veterinary X-Rays","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.21443","title":"Text-Guided Visual Dependency Graph Learning with Cross-Modal Attention Priors","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.22449","title":"EMPIRE: Explicit Manipulation Planning as a Learnable Intermediate Representation for Egocentric Hand-Motion Forecasting","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.28567","title":"GeBDA: Building Damage Assessment as Text-Based Sequence Prediction","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.30510","title":"Lot Machine: Multimodal Lot Extraction from Auction Catalogs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.17458","title":"Tables Decoded: DELTA for Structure, TARQA for Understanding","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.24152","title":"Graded-Relevance Composed Multimodal Retrieval for E-commerce Visual Search at Scale","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.38479","title":"Caption-Mediated Perceived-Safety Estimation for Pedestrian Routing","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04130","title":"Shared Geometry Is Not Shared Physics: A Layerwise Test of the Platonic Representation Hypothesis in Astronomy","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}