Pinned Loading

1. OpenGVLab/LLaMA-Adapter OpenGVLab/LLaMA-Adapter Public

   [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

   Python 5.9k 382

2. ZrrSkywalker/Personalize-SAM ZrrSkywalker/Personalize-SAM Public

   Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds

   Python 1.7k 113

3. AIDE AIDE Public

   「ICLR 2025」 A Sanity Check for AI-generated Image Detection

   Python 289 21

4. OpenGVLab/MUTR OpenGVLab/MUTR Public

   「AAAI 2024」 Referred by Multi-Modality: A Unified Temporal Transformers for Video Object Segmentation

   Python 83 7

5. JaaackHongggg/WorldSense JaaackHongggg/WorldSense Public

   WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

   JavaScript 46 1

6. CrossLMM CrossLMM Public

   CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms

   25