KangarooGroup / Kangaroo
official impelmentation of Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
☆44Updated 3 weeks ago
Related projects: ⓘ
- The official implementation of RAR☆61Updated 5 months ago
- Official repository of MMDU dataset☆61Updated last month
- DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception☆103Updated 3 weeks ago
- Dense Connector for MLLMs☆98Updated last month
- ☆70Updated 4 months ago
- [ECCV2024] Official code implementation of Merlin: Empowering Multimodal LLMs with Foresight Minds☆80Updated 2 months ago
- ☆128Updated 8 months ago
- [EMNLP'23] The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''☆67Updated 5 months ago
- ☆83Updated 9 months ago
- [ECCV 2024] Official PyTorch implementation of DreamLIP: Language-Image Pre-training with Long Captions☆85Updated last week
- This repo contains evaluation code for the paper "Are We on the Right Way for Evaluating Large Vision-Language Models"☆138Updated 5 months ago
- EVE: Encoder-Free Vision-Language Models☆207Updated last month
- Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning☆58Updated 3 months ago
- FreeVA: Offline MLLM as Training-Free Video Assistant☆42Updated 3 months ago
- Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".☆54Updated last year
- A collection of visual instruction tuning datasets.☆74Updated 6 months ago
- A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models!☆114Updated 8 months ago
- ☆100Updated last month
- Official PyTorch Implementation of Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment☆44Updated 3 months ago
- VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation☆84Updated last week
- SVIT: Scaling up Visual Instruction Tuning☆159Updated 3 months ago
- Simple PyTorch implementation of "Libra: Building Decoupled Vision System on Large Language Models" (accepted by ICML 2024)☆41Updated 3 months ago
- Official Dataloader and Evaluation Scripts for LongVideoBench.☆52Updated last month
- ☆58Updated this week
- Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning☆93Updated 2 months ago
- ☆110Updated 4 months ago
- ☆31Updated 3 months ago
- [ECCV 2024] Elysium: Exploring Object-level Perception in Videos via MLLM☆47Updated 2 months ago
- The official implementation of 《MLLMs-Augmented Visual-Language Representation Learning》☆31Updated 6 months ago
- Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆44Updated 3 weeks ago