Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Curso…

🚀 A curated collection of papers focusing on LLM-based quantitative trading.

Official JAX implementation of End-to-End Test-Time Training for Long Context

武汉大学博士/硕士学位论文latex模板（包含插图索引、表格索引、中英文缩略语对照、主要符号表等，字体格式以及排版修正）

Lightweight coding agent that runs in your terminal

The best ChatGPT that $100 can buy.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

An agent-first mobile runtime built on OpenClaw: control apps, learn reusable skills, and connect phones.

A general memory system for agents, powered by deep-research

Official implementation of Accelerating Prefilling for Long-Context Inference via Sparse Pattern Sharing

Unofficial implementations of block/layer-wise pruning methods for LLMs.

Official implementation for LaCo (EMNLP 2024 Findings)

For releasing code related to compression methods for transformers, accompanying our publications

[ICML 2024] Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Official Repo of "MMBench: Is Your Multi-modal Model an All-around Player?"

🚀 A curated list of awesome resources focusing on Context Compression techniques for Large Language Models(LLMs).

CUDA Python: Performance meets Productivity

[COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"

This is the official code for ZLST-Project, Generative Recommendation Benchmark

Official code implementation of Context Cascade Compression: Exploring the Upper Limits of Text Compression

Official repository of RARE: Retrieval-Augmented Reasoning Modeling [KDD 2026 Research Track]

A character-level language diffusion model trained on Tiny Shakespeare

Official PyTorch implementation for "Large Language Diffusion Models"

A quick rundown on each feature and its settings

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs

[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.