| CogVLM2: Visual Language Models for Image and Video Understanding | Aug 29, 2024 | MM-VetMVBench | CodeCode Available | 9 |
| World Model on Million-Length Video And Language With Blockwise RingAttention | Feb 13, 2024 | 4kVideo Understanding | CodeCode Available | 9 |
| Perception Encoder: The best visual embeddings are not at the output of the network | Apr 17, 2025 | Depth EstimationLanguage Modeling | CodeCode Available | 8 |
| GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning | Jul 1, 2025 | document understandingMultimodal Reasoning | CodeCode Available | 7 |
| PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding | Apr 17, 2025 | Video Question AnsweringVideo Understanding | CodeCode Available | 7 |
| VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos | Feb 3, 2025 | Knowledge GraphsRAG | CodeCode Available | 7 |
| InternVideo2: Scaling Foundation Models for Multimodal Video Understanding | Mar 22, 2024 | Action ClassificationAction Recognition | CodeCode Available | 7 |
| CVNets: High Performance Library for Computer Vision | Jun 4, 2022 | Video UnderstandingVocal Bursts Intensity Prediction | CodeCode Available | 6 |
| VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding | Jan 22, 2025 | PhilosophyVideo Question Answering | CodeCode Available | 5 |
| Segment Anything for Videos: A Systematic Survey | Jul 31, 2024 | Image SegmentationRobot Manipulation Generalization | CodeCode Available | 5 |
| OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding | Jun 27, 2024 | DecoderSegmentation | CodeCode Available | 5 |
| ShareGPT4Video: Improving Video Understanding and Generation with Better Captions | Jun 6, 2024 | Video CaptioningVideo Generation | CodeCode Available | 5 |
| VideoMamba: State Space Model for Efficient Video Understanding | Mar 11, 2024 | Action ClassificationMamba | CodeCode Available | 5 |
| Kwai Keye-VL Technical Report | Jul 2, 2025 | Instruction FollowingReinforcement Learning (RL) | CodeCode Available | 4 |
| VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation | May 20, 2025 | MMEMultiple-choice | CodeCode Available | 4 |
| Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models | Apr 21, 2025 | MMEVideo MME | CodeCode Available | 4 |
| VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary | Mar 12, 2025 | EgoSchemaRetrieval | CodeCode Available | 4 |
| Unified Reward Model for Multimodal Understanding and Generation | Mar 7, 2025 | Image Generationmodel | CodeCode Available | 4 |
| Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding | Jan 14, 2025 | Embodied Question AnsweringHallucination | CodeCode Available | 4 |
| Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding | Sep 22, 2024 | Anomaly DetectionGPU | CodeCode Available | 4 |
| Goldfish: Vision-Language Understanding of Arbitrarily Long Videos | Jul 17, 2024 | RetrievalVideo Understanding | CodeCode Available | 4 |
| Tarsier: Recipes for Training and Evaluating Large Video Description Models | Jun 30, 2024 | Video CaptioningVideo Description | CodeCode Available | 4 |
| PVUW 2024 Challenge on Complex Video Understanding: Methods and Results | Jun 24, 2024 | SegmentationSemantic Segmentation | CodeCode Available | 4 |
| MovieChat+: Question-aware Sparse Memory for Long Video Question Answering | Apr 26, 2024 | 2kQuestion Answering | CodeCode Available | 4 |
| PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning | Apr 25, 2024 | Dense CaptioningMVBench | CodeCode Available | 4 |
| MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens | Apr 4, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 4 |
| SnAG: Scalable and Accurate Video Grounding | Apr 2, 2024 | Video GroundingVideo Understanding | CodeCode Available | 4 |
| An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models | Mar 11, 2024 | Computational EfficiencyVideo Understanding | CodeCode Available | 4 |
| Video Understanding with Large Language Models: A Survey | Dec 29, 2023 | SurveyVideo Understanding | CodeCode Available | 4 |
| A Survey on Video Diffusion Models | Oct 16, 2023 | Image GenerationSurvey | CodeCode Available | 4 |
| Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding | Jun 5, 2023 | Language ModelingLanguage Modelling | CodeCode Available | 4 |
| VideoChat: Chat-Centric Video Understanding | May 10, 2023 | Question AnsweringVideo-based Generative Performance Benchmarking | CodeCode Available | 4 |
| InternVideo: General Video Foundation Models via Generative and Discriminative Learning | Dec 6, 2022 | Action ClassificationAction Recognition | CodeCode Available | 4 |
| Flamingo: a Visual Language Model for Few-Shot Learning | Apr 29, 2022 | Few-Shot LearningGenerative Visual Question Answering | CodeCode Available | 4 |
| Flash-VStream: Efficient Real-Time Understanding for Long Video Streams | Jun 30, 2025 | cross-modal alignmentEgoSchema | CodeCode Available | 3 |
| TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos | Apr 24, 2025 | MMEVideo MME | CodeCode Available | 3 |
| VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning | Apr 9, 2025 | MVBenchObject Tracking | CodeCode Available | 3 |
| XAttention: Block Sparse Attention with Antidiagonal Scoring | Mar 20, 2025 | Video GenerationVideo Understanding | CodeCode Available | 3 |
| VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning | Mar 17, 2025 | Grounded Video Question AnsweringQuestion Answering | CodeCode Available | 3 |
| EgoLife: Towards Egocentric Life Assistant | Mar 5, 2025 | Question AnsweringVideo Understanding | CodeCode Available | 3 |
| OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection | Feb 27, 2025 | Action DetectionBenchmarking | CodeCode Available | 3 |
| Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray | Feb 7, 2025 | 4kGeneral Knowledge | CodeCode Available | 3 |
| VideoRoPE: What Makes for Good Video Rotary Position Embedding? | Feb 7, 2025 | HallucinationPosition | CodeCode Available | 3 |
| Valley2: Exploring Multimodal Models with Scalable Vision-Language Design | Jan 10, 2025 | Image CaptioningLanguage Modeling | CodeCode Available | 3 |
| VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM | Dec 31, 2024 | ObjectVideo Understanding | CodeCode Available | 3 |
| VisionZip: Longer is Better but Not Necessary in Vision Language Models | Dec 5, 2024 | Video UnderstandingVisual Question Answering | CodeCode Available | 3 |
| Towards Universal Soccer Video Understanding | Dec 2, 2024 | Action ClassificationSports Understanding | CodeCode Available | 3 |
| Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension | Nov 20, 2024 | GPUMME | CodeCode Available | 3 |
| LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding | Oct 22, 2024 | Token ReductionVideo Question Answering | CodeCode Available | 3 |
| SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference | Oct 6, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 3 |
