| Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder | Jun 28, 2025 | Image SegmentationLarge Language Model | CodeCode Available | 1 |
| LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs | Jun 27, 2025 | Question AnsweringVideo Question Answering | CodeCode Available | 2 |
| How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering? | Jun 19, 2025 | Multiple-choiceQuestion Answering | —Unverified | 0 |
| video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models | Jun 18, 2025 | Audio captioningLarge Language Model | CodeCode Available | 2 |
| CogStream: Context-guided Streaming Video Question Answering | Jun 12, 2025 | Question AnsweringVideo Question Answering | —Unverified | 0 |
| CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models | Jun 11, 2025 | counterfactualDescriptive | CodeCode Available | 2 |
| V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning | Jun 11, 2025 | Action AnticipationLarge Language Model | CodeCode Available | 7 |
| Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning | Jun 9, 2025 | Future predictionQuestion Answering | CodeCode Available | 0 |
| EgoVLM: Policy Optimization for Egocentric Video Understanding | Jun 3, 2025 | EgoSchemaQuestion Answering | CodeCode Available | 0 |
| VUDG: A Dataset for Video Understanding Domain Generalization | May 30, 2025 | Domain GeneralizationMultiple-choice | —Unverified | 0 |
