{"list":"other","total":55,"rows":[{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2409.14485","title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding","created":"2024-09-22","cited_by_count":213},{"id":"2403.14003","title":"Multi-Modal Hallucination Control by Visual Information Grounding","created":"2024-03-20","cited_by_count":208},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"id":"2410.19702","title":"TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning","created":"2024-10-25","cited_by_count":106},{"id":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101},{"id":"2603.21687","title":"MIRAGE: The Illusion of Visual Understanding","created":"2026-03-23","cited_by_count":65},{"id":"2511.20785","title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","created":"2025-11-25","cited_by_count":61},{"id":"2411.04923","title":"VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","created":"2024-11-07","cited_by_count":51},{"id":"2503.18478","title":"Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding","created":"2025-03-24","cited_by_count":49},{"id":"2503.11579","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","created":"2025-03-14","cited_by_count":36},{"id":"2508.20478","title":"Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding","created":"2025-08-28","cited_by_count":28},{"id":"2508.04369","title":"TSPO: Temporal Sampling Policy Optimization for Long-form Video Language Understanding","created":"2025-08-06","cited_by_count":25},{"id":"2510.20470","title":"Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence","created":"2025-10-23","cited_by_count":18},{"id":"2512.04000","title":"Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding","created":"2025-12-03","cited_by_count":11},{"id":"2606.26387","title":"Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs","created":"2026-06-24","cited_by_count":8},{"id":"2602.04094","title":"VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding","created":"2026-02-04","cited_by_count":7},{"id":"2603.00983","title":"Event-Anchored Frame Selection for Effective Long-Video Understanding","created":"2026-03-01","cited_by_count":7},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6},{"id":"2605.07106","title":"Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning","created":"2026-05-08","cited_by_count":6},{"id":"2506.17901","title":"PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs","created":"2025-06-22","cited_by_count":5},{"id":"2510.20622","title":"SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding","created":"2025-10-23","cited_by_count":5},{"id":"2511.12530","title":"ReaSon: Reinforced Causal Search with Information Bottleneck for Video Understanding","created":"2025-11-16","cited_by_count":5},{"id":"2605.12882","title":"CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence","created":"2026-05-13","cited_by_count":5},{"id":"2606.02522","title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","created":"2026-06-01","cited_by_count":5},{"id":"2606.13870","title":"Mirage Probes: How Vision Models Fake Visual Understanding","created":"2026-06-11","cited_by_count":5},{"id":"2605.20676","title":"VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence","created":"2026-05-20","cited_by_count":4},{"id":"2607.09880","title":"CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series","created":"2026-07-10","cited_by_count":4},{"id":"2603.05663","title":"Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding","created":"2026-03-05","cited_by_count":3},{"id":"2604.12424","title":"Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation","created":"2026-04-14","cited_by_count":3},{"id":"2604.21814","title":"Divide-then-Diagnose: Weaving Clinician-Inspired Contexts for Ultra-Long Capsule Endoscopy Videos","created":"2026-04-23","cited_by_count":3},{"id":"2607.00115","title":"PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking","created":"2026-06-30","cited_by_count":2},{"id":"2605.26104","title":"EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding","created":"2026-05-25","cited_by_count":1},{"id":"2606.05736","title":"VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning","created":"2026-06-04","cited_by_count":1},{"id":"2606.07872","title":"VisualFLIP: Do Predictions Depend on Task-Critical Visual Evidence in Multimodal Reasoning?","created":"2026-06-05","cited_by_count":1},{"id":"2607.25947","title":"A Cost-Effective Multimodal LLM Reasoning Framework for Question Answering over Irregular Clinical Time Series","created":"2026-07-28","cited_by_count":1}],"next_cursor":null}