{"total":43,"rows":[{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2409.17531","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","created":"2024-09-26","cited_by_count":36,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20,"area":null},{"id":"2412.09601","title":"TimeRefine: Temporal Grounding with Time Refining Video LLM","created":"2024-12-12","cited_by_count":15,"area":null},{"id":"2505.24138","title":"AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuits","created":"2025-05-30","cited_by_count":15,"area":null},{"id":"2504.01020","title":"Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation","created":"2025-04-01","cited_by_count":13,"area":null},{"id":"2506.17873","title":"SurgVidLM: Towards Multi-grained Surgical Video Understanding with Large Language Model","created":"2025-06-22","cited_by_count":13,"area":null},{"id":"2504.13621","title":"Visual Intention Grounding for Egocentric Assistants","created":"2025-04-18","cited_by_count":11,"area":null},{"id":"2509.04833","title":"PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2410.02505","title":"Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2512.03666","title":"ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos","created":"2025-12-03","cited_by_count":8,"area":null},{"id":"2502.20104","title":"New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2505.24329","title":"DisTime: Distribution-based Time Representation for Video Large Language Models","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2508.07925","title":"TAG: A Simple Yet Effective Temporal-Aware Approach for Zero-Shot Video Temporal Grounding","created":"2025-08-11","cited_by_count":7,"area":null},{"id":"2504.01476","title":"Enhanced Cross-modal 3D Retrieval via Tri-modal Reconstruction","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2504.06393","title":"The Zero Body Problem: Probing LLM Use of Sensory Language","created":"2025-04-08","cited_by_count":5,"area":null},{"id":"2511.16937","title":"OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2601.00584","title":"GranAlign: Granularity-Aware Alignment Framework for Zero-Shot Video Moment Retrieval","created":"2026-01-02","cited_by_count":5,"area":null},{"id":"2512.24097","title":"Factorized Learning for Temporally Grounded Video-Language Models","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2504.02876","title":"Multimodal Reference Visual Grounding","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2603.28757","title":"SonoWorld: From One Image to a 3D Audio-Visual Scene","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2512.10363","title":"Point to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videos","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2602.10230","title":"Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2603.26646","title":"Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2605.21796","title":"MM-Conv: A Multimodal Dataset and Benchmark for Context-Aware Grounding in 3D Dialogue","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2607.28516","title":"Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video Understanding","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2507.04522","title":"Grounded Gesture Generation: Language, Motion, and Space","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2508.06317","title":"Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Temporal Grounding","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2508.17890","title":"UniAPO: Unified Multimodal Automated Prompt Optimization","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2512.01312","title":"IVCR-200K: A Large-Scale Multi-turn Dialogue Benchmark for Interactive Video Corpus Retrieval","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2601.01526","title":"BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2603.04128","title":"Crab$^{+}$: A Scalable and Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.06973","title":"T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2604.10527","title":"STORM: End-to-End Referring Multi-Object Tracking in Videos","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2607.00672","title":"DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2503.23990","title":"BeMERC: Behavior-Aware MLLM-based Framework for Multimodal Emotion Recognition in Conversation","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2604.02323","title":"Beyond Referring Expressions: Scenario Comprehension Visual Grounding","created":"2026-04-02","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":"2608.30584","title":"Learning Compositional Spatio-Temporal Video Grounding with Synthetic Curriculum","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}