Unified KV Cache Compression Methods for Auto-Regressive Models
Learning to Reason with Search for LLMs via Reinforcement Learning
Advanced LLM-powered brute-force tool combining AI intelligence
Traditional Mandarin LLMs for Taiwan
Benchmark LLMs by fighting in Street Fighter 3
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
Recipes to train reward model for RLHF
A tension reasoning engine over 131 S-class problems
Constrained Value Alignment via Safe Reinforcement Learning
Unleashing 10,000+ Word Generation from Long Context LLMs
AI Powered Knowledge Graph Generator
Autoregressive Model Beats Diffusion
An agentless approach to automatically solve software development
Empowering Code Generation with OSS-Instruct
Neural Network architecture based on ideas of the original LSTM
A simple, performant and scalable Jax LLM
A lightweight framework for building LLM-based agents
The SOTA Open-Source Browser Agent
The Cradle framework is a first attempt at General Computer Control
Overcoming Group Chat Scenarios with LLM-based Technical Assistance
LISA: Reasoning Segmentation via Large Language Model
Enhances Tesseract OCR output using LLMs (local or API)
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System
Implementation for MatMul-free LM
Leaderboard Comparing LLM Performance at Producing Hallucinations