{"total":70,"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":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202,"area":null},{"id":"2503.11187","title":"FastVID: Dynamic Density Pruning for Fast Video Large Language Models","created":"2025-03-14","cited_by_count":52,"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":"2502.12081","title":"Unhackable Temporal Rewarding for Scalable Video MLLMs","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2505.05456","title":"SITE: towards Spatial Intelligence Thorough Evaluation","created":"2025-05-08","cited_by_count":29,"area":null},{"id":"2507.13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","created":"2025-07-17","cited_by_count":29,"area":null},{"id":"2503.06764","title":"SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation","created":"2025-03-09","cited_by_count":21,"area":null},{"id":"2504.02949","title":"VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning","created":"2025-04-03","cited_by_count":21,"area":null},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2502.03183","title":"MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding","created":"2025-02-05","cited_by_count":18,"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":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2410.10783","title":"LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2505.04601","title":"OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning","created":"2025-05-07","cited_by_count":16,"area":null},{"id":"2505.23522","title":"OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data","created":"2025-05-29","cited_by_count":14,"area":null},{"id":"2507.19599","title":"Object-centric Video Question Answering with Visual Grounding and Referring","created":"2025-07-25","cited_by_count":13,"area":null},{"id":"2602.08683","title":"OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2504.20041","title":"Learning Streaming Video Representation via Multitask Training","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2504.16030","title":"LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale","created":"2025-04-22","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":"2510.02262","title":"From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding","created":"2025-10-02","cited_by_count":9,"area":null},{"id":"2510.02778","title":"AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2503.22215","title":"Learning to Instruct for Visual Instruction Tuning","created":"2025-03-28","cited_by_count":8,"area":null},{"id":"2504.09282","title":"VideoAds for Fast-Paced Video Understanding","created":"2025-04-12","cited_by_count":8,"area":null},{"id":"2505.16175","title":"QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2509.26636","title":"AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2603.25072","title":"GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding","created":"2026-03-26","cited_by_count":8,"area":null},{"id":"2505.24840","title":"The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2512.03575","title":"UniComp: Rethinking Video Compression Through Informational Uniqueness","created":"2025-12-03","cited_by_count":7,"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":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2510.07959","title":"DISCO: Diversifying Sample Condensation for Efficient Model Evaluation","created":"2025-10-09","cited_by_count":5,"area":null},{"id":"2510.20622","title":"SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding","created":"2025-10-23","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":"2605.10343","title":"EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2509.14199","title":"Dense Video Understanding with Gated Residual Tokenization","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2605.12056","title":"OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2606.07289","title":"Closed-Form Spectral Regularization for Multi-Task Model Merging","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2606.17574","title":"DeepInsight: A Unified Evaluation Infrastructure Across the Physical AI Stack","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2505.18115","title":"Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2604.10784","title":"TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2605.13737","title":"Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.22823","title":"Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2505.23308","title":"Spoken question answering for visual queries","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2605.12960","title":"DiM\\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging","created":"2026-05-13","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":"2607.05090","title":"Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2505.07531","title":"QuantX: A Framework for Hardware-Aware Quantization of Generative AI Workloads","created":"2025-05-12","cited_by_count":0,"area":null},{"id":"2506.11515","title":"Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2509.08031","title":"AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2510.06071","title":"Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2512.05385","title":"ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2512.14620","title":"JMMMU-Pro: Image-based Japanese Multi-discipline Multimodal Understanding Benchmark via Vibe Benchmark Construction","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.06127","title":"Compressing LLMs with MoP: Mixture of Pruners","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.08077","title":"AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.07355","title":"TTF: Temporal Token Fusion for Efficient Video-Language Model","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.03871","title":"Visual Instruction Tuning Aligns Modalities through Abstraction","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":"2606.31326","title":"Bridging Video Understanding and Generation in a Unified Framework","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.09488","title":"SigLIP-HD by Fine-to-Coarse Supervision","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.26317","title":"Modality Maturity Index: A benchmark for assessing multimodal capabilities of omni models","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.27929","title":"Training-Free Temporal Abstraction for General Video Understanding","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.37564","title":"Orthogonal Yet Coupled: Decoupling Geometric Components for Model Merging","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.05978","title":"Byte Language Models: Scaling, Emergent Abstractions, and Information Allocation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.18535","title":"Meta-Video: Efficient Standardized Evaluation for Video Understanding","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}