TIGER-AI-Lab / VISTALinks
The code for "VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by VIdeo SpatioTemporal Augmentation" [CVPR2025]
☆19Updated 5 months ago
Alternatives and similar repositories for VISTA
Users that are interested in VISTA are comparing it to the libraries listed below
Sorting:
- M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning☆40Updated last month
- Official implementation of Next Block Prediction: Video Generation via Semi-Autoregressive Modeling☆38Updated 6 months ago
- ☆31Updated last year
- ☆70Updated 2 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆66Updated last month
- [NeurIPS-24] This is the official implementation of the paper "DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effect…☆39Updated last year
- Multimodal RewardBench☆45Updated 6 months ago
- Implementation and dataset for paper "Can MLLMs Perform Text-to-Image In-Context Learning?"☆41Updated 2 months ago
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆83Updated 5 months ago
- [ICCV 2025] Dynamic-VLM☆23Updated 8 months ago
- Code for the paper "Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers" [ICCV 2025]☆82Updated 3 weeks ago
- ☆43Updated 9 months ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆55Updated 8 months ago
- [ECCV 2024] Learning Video Context as Interleaved Multimodal Sequences☆40Updated 5 months ago
- [CVPR 2025] PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models☆45Updated 2 months ago
- ☆12Updated 7 months ago
- [ICLR 2025] Source code for paper "A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegr…☆77Updated 8 months ago
- ☆45Updated 7 months ago
- Official InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows☆15Updated last week
- VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs☆48Updated 5 months ago
- On Path to Multimodal Generalist: General-Level and General-Bench☆19Updated last month
- Official implementation of "Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology"☆56Updated last month
- Codes for ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding [ICML 2025]]☆37Updated last month
- [ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark☆124Updated 2 months ago
- Unifying Specialized Visual Encoders for Video Language Models☆22Updated last month
- Quick Long Video Understanding☆62Updated 2 months ago
- Code for "CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning"☆22Updated 5 months ago
- ☆52Updated 2 weeks ago
- HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆63Updated 6 months ago
- ☆23Updated 2 months ago