{"total":81,"rows":[{"id":"2501.12386","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","created":"2025-01-21","cited_by_count":211,"area":"mllm"},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146,"area":"mllm"},{"id":"2601.10611","title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","created":"2026-01-15","cited_by_count":139,"area":"mllm"},{"id":"2503.23765","title":"STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?","created":"2025-03-31","cited_by_count":79,"area":"mllm"},{"id":"2509.24871","title":"StreamForest: Efficient Online Video Understanding with Persistent Event Memory","created":"2025-09-29","cited_by_count":78,"area":"mllm"},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64,"area":"mllm"},{"id":"2503.18478","title":"Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding","created":"2025-03-24","cited_by_count":49,"area":"mllm"},{"id":"2605.25979","title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","created":"2026-05-25","cited_by_count":39,"area":"mllm"},{"id":"2504.02438","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","created":"2025-04-03","cited_by_count":37,"area":"mllm"},{"id":"2506.19225","title":"Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification","created":"2025-06-24","cited_by_count":37,"area":"mllm"},{"id":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32,"area":"mllm"},{"id":"2506.18883","title":"Universal Video Temporal Grounding with Generative Multi-modal Large Language Models","created":"2025-06-23","cited_by_count":27,"area":"mllm"},{"id":"2504.16083","title":"MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention","created":"2025-04-22","cited_by_count":26,"area":"mllm"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2503.14935","title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","created":"2025-03-19","cited_by_count":24,"area":"mllm"},{"id":"2505.14640","title":"VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation","created":"2025-05-20","cited_by_count":21,"area":"mllm"},{"id":"2505.21333","title":"MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios","created":"2025-05-27","cited_by_count":18,"area":"mllm"},{"id":"2509.18056","title":"TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs","created":"2025-09-22","cited_by_count":15,"area":"mllm"},{"id":"2603.28069","title":"MolmoPoint: Better Pointing for VLMs with Grounding Tokens","created":"2026-03-30","cited_by_count":15,"area":"mllm"},{"id":"2603.03985","title":"RIVER: A Real-Time Interaction Benchmark for Video LLMs","created":"2026-03-04","cited_by_count":14,"area":"mllm"},{"id":"2503.22610","title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","created":"2025-03-28","cited_by_count":11,"area":"mllm"},{"id":"2505.17020","title":"CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms","created":"2025-05-22","cited_by_count":11,"area":"mllm"},{"id":"2506.01674","title":"MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs","created":"2025-06-02","cited_by_count":11,"area":"mllm"},{"id":"2510.02295","title":"VideoNSA: Native Sparse Attention Scales Video Understanding","created":"2025-10-02","cited_by_count":11,"area":"mllm"},{"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,"area":"mllm"},{"id":"2511.07250","title":"MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs","created":"2025-11-10","cited_by_count":10,"area":"mllm"},{"id":"2603.12254","title":"Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing","created":"2026-03-12","cited_by_count":9,"area":"mllm"},{"id":"2603.26586","title":"MA-Bench: Towards Fine-grained Micro-Action Understanding","created":"2026-03-27","cited_by_count":9,"area":"mllm"},{"id":"2504.15270","title":"An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes","created":"2025-04-21","cited_by_count":7,"area":"mllm"},{"id":"2506.04953","title":"APVR: Hour-Level Long Video Understanding with Adaptive Pivot Visual Information Retrieval","created":"2025-06-05","cited_by_count":7,"area":"mllm"},{"id":"2510.17722","title":"MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues","created":"2025-10-20","cited_by_count":7,"area":"mllm"},{"id":"2511.19524","title":"VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning","created":"2025-11-24","cited_by_count":6,"area":"mllm"},{"id":"2606.24422","title":"EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding","created":"2026-06-23","cited_by_count":6,"area":"mllm"},{"id":"2508.00399","title":"iSafetyBench: A video-language benchmark for safety in industrial environment","created":"2025-08-01","cited_by_count":5,"area":"mllm"},{"id":"2603.19571","title":"CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management","created":"2026-03-20","cited_by_count":5,"area":"mllm"},{"id":"2604.08120","title":"Small Vision-Language Models are Smart Compressors for Long Video Understanding","created":"2026-04-09","cited_by_count":5,"area":"mllm"},{"id":"2604.14149","title":"One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding","created":"2026-04-15","cited_by_count":5,"area":"mllm"},{"id":"2608.25356","title":"Where to Look Matters: On-Policy Self-Distillation for Long-Video Understanding","created":"2026-08-26","cited_by_count":5,"area":"mllm"},{"id":"2507.23284","title":"Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval","created":"2025-07-31","cited_by_count":4,"area":"mllm"},{"id":"2511.16595","title":"TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding","created":"2025-11-20","cited_by_count":4,"area":"mllm"},{"id":"2512.16250","title":"AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding","created":"2025-12-18","cited_by_count":4,"area":"mllm"},{"id":"2503.18712","title":"LLaVAction: evaluating and training multi-modal large language models for action understanding","created":"2025-03-24","cited_by_count":3,"area":"mllm"},{"id":"2506.13564","title":"State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models","created":"2025-06-16","cited_by_count":3,"area":"mllm"},{"id":"2508.03009","title":"Enhancing Long Video Question Answering with Scene-Localized Frame Grouping","created":"2025-08-05","cited_by_count":3,"area":"mllm"},{"id":"2602.03230","title":"EventFlash: Towards Efficient MLLMs for Event-Based Vision","created":"2026-02-03","cited_by_count":3,"area":"mllm"},{"id":"2603.13119","title":"Geometry-Guided Camera Motion Understanding in VideoLLMs","created":"2026-03-13","cited_by_count":3,"area":"mllm"},{"id":"2605.06537","title":"MedHorizon: Towards Long-context Medical Video Understanding in the Wild","created":"2026-05-07","cited_by_count":3,"area":"mllm"},{"id":"2606.24286","title":"AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression","created":"2026-06-23","cited_by_count":3,"area":"mllm"},{"id":"2607.17423","title":"TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs","created":"2026-07-19","cited_by_count":3,"area":"mllm"},{"id":"2507.01492","title":"AVC-DPO: Aligned Video Captioning via Direct Preference Optimization","created":"2025-07-02","cited_by_count":2,"area":"mllm"},{"id":"2601.05495","title":"MMViR: A Multi-Modal and Multi-Granularity Representation for Long-range Video Understanding","created":"2026-01-09","cited_by_count":2,"area":"mllm"},{"id":"2603.07071","title":"VirtueBench: Evaluating Trustworthiness under Uncertainty in Long Video Understanding","created":"2026-03-07","cited_by_count":2,"area":"mllm"},{"id":"2603.28696","title":"AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding","created":"2026-03-30","cited_by_count":2,"area":"mllm"},{"id":"2604.04372","title":"Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning","created":"2026-04-06","cited_by_count":2,"area":"mllm"},{"id":"2512.09907","title":"VisualActBench: Can VLMs See and Act like a Human?","created":"2025-12-10","cited_by_count":1,"area":"mllm"},{"id":"2512.19535","title":"CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion","created":"2025-12-22","cited_by_count":1,"area":"mllm"},{"id":"2602.00559","title":"Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models","created":"2026-01-31","cited_by_count":1,"area":"mllm"},{"id":"2605.21954","title":"MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2605.31598","title":"Linear Scaling Video VLMs for Long Video Understanding","created":"2026-05-29","cited_by_count":1,"area":"mllm"},{"id":"2608.02078","title":"CAVE: Competence-Aware Visual Boundary Evidence Alignment for Video Temporal Grounding","created":"2026-08-03","cited_by_count":1,"area":"mllm"},{"id":"2608.05707","title":"One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding","created":"2026-08-06","cited_by_count":1,"area":"mllm"},{"id":"2608.12209","title":"Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction","created":"2026-08-12","cited_by_count":1,"area":"mllm"},{"id":"2608.21430","title":"Evaluating Multimodal Narrative Understanding of Popular Hollywood Films","created":"2026-08-17","cited_by_count":1,"area":"mllm"},{"id":"2608.27881","title":"StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models","created":"2026-08-28","cited_by_count":1,"area":"mllm"},{"id":"2609.35507","title":"ReVA: A Scene-Centric Dataset Beyond Repetition for Remote Sensing Video Question Answering","created":"2026-09-28","cited_by_count":1,"area":"mllm"},{"id":"2609.38597","title":"PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation","created":"2026-09-29","cited_by_count":1,"area":"mllm"},{"id":"2603.19481","title":"Narrative Aligned Long Form Video Question Answering","created":"2026-03-19","cited_by_count":0,"area":"mllm"},{"id":"2605.08974","title":"Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models","created":"2026-05-09","cited_by_count":0,"area":"mllm"},{"id":"2605.13080","title":"Learning to See What You Need: Gaze Attention for Multimodal Large Language Models","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2606.06853","title":"MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models","created":"2026-06-05","cited_by_count":0,"area":"mllm"},{"id":"2606.31187","title":"Learning to Deny: Action Denial in Multimodal Large Language Models","created":"2026-06-30","cited_by_count":0,"area":"mllm"},{"id":"2608.08315","title":"Your VLM Already Knows When: Training-Free Temporal Grounding by Asking Yes or No","created":"2026-08-08","cited_by_count":0,"area":"mllm"},{"id":"2609.02565","title":"MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval?","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.29607","title":"STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models","created":"2026-08-28","cited_by_count":0,"area":"mllm"},{"id":"2609.34581","title":"Counterfactual Attention Policy Distillation for Temporal Video Grounding","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.37426","title":"LazySloth: Bounded LLM-based Lazy Tree Search for Fast Long Video Comprehension","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2609.40055","title":"Less Data, Better Timing: Student-Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding","created":"2026-09-30","cited_by_count":0,"area":"mllm"},{"id":"2610.00573","title":"FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering","created":"2026-09-30","cited_by_count":0,"area":"mllm"},{"id":"2610.04225","title":"FlashGaze: Training-Free Multi-Scale Patch Pruning For Efficient Video Understanding","created":"2026-10-03","cited_by_count":0,"area":"mllm"},{"id":"2610.16118","title":"Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding","created":"2026-10-12","cited_by_count":0,"area":"mllm"},{"id":"2610.17242","title":"When Left Is Right? Camera-Motion Understanding beyond Screen","created":"2026-10-12","cited_by_count":0,"area":"mllm"}],"next_cursor":null}