-
Tsinghua University
- Beijing, China
-
08:05
(UTC +08:00) - zeonlap.github.io
Highlights
- Pro
Starred repositories
RAGEN is the first open-source reproduction of DeepSeek-R1 for training agentic models via reinforcement learning.
EvaByte: Efficient Byte-level Language Models at Scale
Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
Scalable RL solution for advanced reasoning of language models
[TPAMI reviewing] Towards Visual Grounding: A Survey
Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…
🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.
A collection of recent papers on building autonomous agent. Two topics included: RL-based / LLM-based agents.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
GUI Grounding for Professional High-Resolution Computer Use
Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Building a comprehensive and handy list of papers for GUI agents
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
Official Implementation of Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Team Optimization
A series of math-specific large language models of our Qwen2 series.
nwiad / verl
Forked from volcengine/verlveRL: Volcano Engine Reinforcement Learning for LLM
Development repository for the Triton language and compiler
A high-throughput and memory-efficient inference and serving engine for LLMs
Simple, unified interface to multiple Generative AI providers
Ongoing research training transformer models at scale
A passive recording project allows you to have complete control over your data. Automatically take screenshots of all your screens, index them, and save them locally.