Tianle Li
Designation

Tianle Li

MTS // xAI // RL, Reasoning
firstlast@berkeley.edu
Sync Ratio
0%
Neural Activation Reinforcement Learning Sector: SF Status: Nominal
Personnel File

I am a Member of Technical Staff at xAI, currently on the Science of RL team. I also work on post-training and reasoning.

Contributions since May 2025
Record

Previously, I was an EECS undergraduate at UC Berkeley (2021–2025), where I was fortunate to be advised by Ion Stoica and built LMArena.

During my undergrad, I also spent a year full-time at Nexusflow as part of the LLM post-training team, working with Banghua Zhu and Jiantao Jiao. Additionally, I briefly interned as a student researcher at Google AI Research, where I was working on reasoning.

Research Missions

I am very interested in fundamental problems in training large models and solving superintelligence.

Open problems
  1. Can we get more than 1-bit of information per rollout in RL?
  2. Can we skip mid-training? Can a model learn on the fly?