Code of BRIDGE: Building Reinforcement-Learning Depth-to-Image Data Generation Engine for Monocular Depth Estimation

[ICML 2025 Oral] Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents.

[ACL 2025 Best Theme Paper] This is the official implementation for the paper: "Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models"

Tools for OpenDataArena: Fair, Open, and Transparent Arena for Data

Dingo: A Comprehensive AI Data Quality Evaluation Tool

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.

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.

SECOM: On Memory Construction and Retrieval for Personalized Conversational Agents, ICLR 2025

The Code and Script of "David's Slingshot: A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis"

A python script for downloading huggingface datasets and models.

一个基于 Mistral API 的 OCR 工具，支持 PDF 和图片文件的文字识别，并提供 Markdown 格式的预览功能

[EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs

Awesome Long-CoT Data

"From Trojan Horses to Castle Walls: Unveiling Bilateral Backdoor Effects in Diffusion Models" by Zhuoshi Pan*, Yuguang Yao*, Gaowen Liu, Bingquan Shen, H. Vicky Zhao, Ramana Rao Kompella, Sijia Liu

Optimizing inference proxy for LLMs

Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".

Official repository for InvestAlign: Align LLMs with Investor Decision-Making under Herd Behavior

✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

头顶冒火🤯文档

This is the official project of paper: Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

Smart Energy Project

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.