{"total":43,"rows":[{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2412.16256","title":"Aria-UI: Visual Grounding for GUI Instructions","created":"2024-12-20","cited_by_count":140,"area":null},{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2410.15458","title":"Allegro: Open the Black Box of Commercial-Level Video Generation Model","created":"2024-10-20","cited_by_count":70,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2410.07752","title":"Lost in Time: A New Temporal Benchmark for VideoLLMs","created":"2024-10-10","cited_by_count":42,"area":null},{"id":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37,"area":null},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2503.21821","title":"Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving","created":"2025-03-26","cited_by_count":31,"area":null},{"id":"2502.12782","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","created":"2025-02-18","cited_by_count":23,"area":null},{"id":"2510.12422","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding","created":"2025-10-14","cited_by_count":22,"area":null},{"id":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","cited_by_count":21,"area":null},{"id":"2506.00993","title":"FlexSelect: Flexible Token Selection for Efficient Long Video Understanding","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2509.24365","title":"Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models","created":"2025-09-29","cited_by_count":18,"area":null},{"id":"2503.21459","title":"RoadSocial: A Diverse VideoQA Dataset and Benchmark for Road Event Understanding from Social Video Narratives","created":"2025-03-27","cited_by_count":15,"area":null},{"id":"2505.22810","title":"VidText: Towards Comprehensive Evaluation for Video Text Understanding","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2410.22217","title":"Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2505.23484","title":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","created":"2025-05-29","cited_by_count":9,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2602.13013","title":"Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions","created":"2026-02-13","cited_by_count":9,"area":null},{"id":"2506.21742","title":"VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2506.03990","title":"DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2602.20913","title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2504.06835","title":"LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2512.23483","title":"TV-RAG: A Temporal-aware and Semantic Entropy-Weighted Framework for Long Video Retrieval and Understanding","created":"2025-12-29","cited_by_count":6,"area":null},{"id":"2412.11906","title":"PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2506.13888","title":"VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2608.05000","title":"Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2503.06885","title":"ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2503.09279","title":"Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2506.13277","title":"SeqPE: Transformer with Sequential Position Encoding","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2508.13692","title":"HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2509.08538","title":"MESH -- Understanding Videos Like Human: Measuring Hallucinations in Large Video Models","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2606.13289","title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2505.19853","title":"Two Causally Related Needles in a Video Haystack","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2511.18055","title":"IE-Critic-R1: Advancing the Explanatory Measurement of Text-Driven Image Editing for Human Perception Alignment","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2602.13033","title":"Buy versus Build an LLM: A Decision Framework for Governments","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2510.03955","title":"Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2606.20970","title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2609.05596","title":"Time-Aware Assistive Navigation","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.03109","title":"Emergent Structure in the Marginal Attention Space of Language Models","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}