Jiaxun Cui 🐿️

Jiaxun Cui 🐿️ works as a research scientist at Google on agent post-training and evaluation for Gemini. He earned a PhD in electrical and computer engineering at the University of Texas at Austin, where his research included multi-agent learning, communication between autonomous vehicles, and agents that can generalize across teammates and opponents.

Career

Cosigned byLoading...

CosignedSign in to view

Based in: Mountain View
Elsewhere

University of Texas - Austin

Electrical and Computer Engineering PhD degree

Products & media

cuijiaxun.github.io

Communication and Generalization in Multi-Agent Learning

Read his dissertation research on training agents to communicate and generalize across partners, including work on cooperative driving and multi-agent policies.

Writing

ut-austin-rpl.github.io

Coopernaut: End-to-End Driving with Cooperative Perception for Networked Vehicles

Explore a cooperative-driving system that shares compact vehicle perception over wireless channels, along with its evaluation in simulated driving scenarios.

ifaamas.org

Communication and Generalization in Multi-Agent Learning: Doctoral Consortium

Read his overview of research on agent generalization, communication, and human-AI interaction in settings such as autonomous driving.

Writing

humanoidsoccer.github.io

Learning Agile Striker Skills for Humanoid Soccer Robots from Noisy Sensory Input

Learn about a reinforcement-learning pipeline for helping humanoid soccer robots kick accurately despite noisy sensing and changing conditions.

neurips.cc

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Read research evaluating whether language-model agents can cooperate across varied social scenarios and partners.

Writing

Profile name

Company name

Company name

Profile name

Company name

Company name

Profile name

Company name

Company name

Profile name

Company name

Company name

Profile name

Company name

Company name

Jiaxun Cui 🐿️

University of Texas - Austin

Products & media

Communication and Generalization in Multi-Agent Learning

Coopernaut: End-to-End Driving with Cooperative Perception for Networked Vehicles

Communication and Generalization in Multi-Agent Learning: Doctoral Consortium

Learning Agile Striker Skills for Humanoid Soccer Robots from Noisy Sensory Input

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Curated Lists

List Inclusions