[ICLR'25] Official code for the paper 'MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs'

We introduce BabyVision, a benchmark revealing the infancy of AI vision.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

The open source coding agent.

A hyperparameter optimization framework

GhostRAG: Extracting Data from Retrieval-Augmented Generation of Large Language Models via Auto-constructed Prompt Injections

⏰ Collaboratively track worldwide conference deadlines (Website, Python Cli, Wechat Applet) / If you find it useful, please star this project, thanks~

Code and source for paper ``How to Fine-Tune BERT for Text Classification?``

Spark RAPIDS plugin - accelerate Apache Spark with GPUs

Free Introduction to Bash Scripting eBook

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

Dynamic visualization display the route map of Beijing subway. 动态可视化展示北京地铁运行图。

Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"

All Algorithms implemented in Python

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫

Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University

中文翻译的 Hands-On-Large-Language-Models (hands-on-llms)，动手学习大模型

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Official style files for papers submitted to venues of the Association for Computational Linguistics

[Medical_NLP ➟ Awesome-AI4Med] medical-related LLMs, Multimodal systems, Datasets, Benchmarks, and more.

[NeurIPS25 Spotlight] Official Implementation for CBSA (Contract-and-Broadcast Self-Attention)

A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.

Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts

[NeurIPS 2025] The official PyTorch implementation of the "Vision Function Layer in MLLM".

Ongoing research training transformer models at scale

S4AL: Self-Supervised Vessel Segmentation with Synthetic Medical Images via Adversarial Learning