I'm a Research Engineer and my primary focus is on advancing the field of artificial intelligence, particularly in the areas of Large Language Models (LLMs), Multimodal Language Models, and End-to-End Agent Systems.

I entered the large model industry in 2023, gaining comprehensive experience across the entire pipeline of LLM/MLLM pre-training, Supervised Fine-Tuning (SFT), and Reinforcement Learning (RL). I have an in-depth understanding of the nuances at each stage and remain continually amazed by the rapid evolution of this industry.

Prior to this, I was responsible for recommendation system at a leading social media.

• Large Language Models (LLMs): Exploring the capabilities and applications of LLMs in various domains.
• Multimodal Language Models: Working on models that can understand and generate content across multiple modalities (text, image, audio, etc.).
• Agent & Operator Systems: Developing intelligent agents that can operate autonomously and efficiently in complex environments.

• Email: [[email protected]]

• Advanced techniques in MLLM RL and end2end RL.
• Multimodal model integration and deployment.

• Projects related to LLMs, multimodal AI, and autonomous agents.
• Open-source contributions in AI and machine learning.

I love exploring the intersection of AI and creativity, and I believe that AI can be a powerful tool for enhancing human potential.