Stars
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
BEACON: Benchmark for Comprehensive RNA Tasks and Language Models
Data annotation toolbox supports image, audio and video data.
The Open-Source Data Annotation Platform
A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具,支持PDF/网页/多格式电子书提取。
Reasoning in Large Language Models: Papers and Resources, including Chain-of-Thought and OpenAI o1 🍓
`dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.
code for Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning
Official Implementation of FreeDrag (CVPR 2024)
Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation
An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
Official implementation of Bootstrap3D: Improving 3D Content Creation with Synthetic Data
zer0int / Long-CLIP
Forked from beichenzbc/Long-CLIPScripts for use with LongCLIP, including fine-tuning Long-CLIP
An open-source implementation for training LLaVA-NeXT.
Monte Carlo simulation of phase change for simple cubic lattice. This is my course project for "Computational Physics".
Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
[AAAI 2021] Initiative Defense against Facial Manipulation
[ICCV 2023] Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting
[CVPR 2022] Shape-invariant Adversarial Point Clouds
[TIP 2024] PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition
Papers about Hallucination in Multi-Modal Large Language Models (MLLMs)
[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"