ML engineer and mechanistic interpretability researcher working on agents.
Email: [email protected]
ML engineer and mechanistic interpretability researcher working on agents.
Email: [email protected]
LSLM implements full duplex modeling in interactive speech language models, based on research by Ma et al. (2024). This project advances human-computer interaction through real-time spoken dialogue…
This my attempt to create Self-Correcting-LLM based on the paper Training Language Models to Self-Correct via Reinforcement Learning by google
This project implements an efficient scheduling system for Large Language Model (LLM) inference, as described in the paper "Efficient LLM Scheduling by Learning to Rank"
Python 9