Products

AI Research

Resources

About

Products

Yuandong Tian

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

Yuandong is a Research Scientist working on deep reinforcement learning and its applications on games, and theoretical analysis of deep models. He is the Lead Scientist and Engineer for ELF OpenGo and DarkForest Go project. Prior to that, he was a researcher and engineer on the Google Self-driving Car team. Yann received a Ph.D. in Robotics Institute, Carnegie Mellon University, and a Bachelor's and Master's degree of Computer Science in Shanghai Jiao Tong University. He is the recipient of ICCV 2013 Marr Prize Honorable Mentions.

Research Areas

Computer Vision

Core Machine Learning

Natural Language Processing (NLP)

Reinforcement Learning

Systems Research

Theory

Yuandong's Work

ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

darkforestGO Github Repository

FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

Yuandong's Publications

October 13, 2025

REINFORCEMENT LEARNING

RESEARCH

SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

Paria Rashidinejad, Cai Zhou, Tommi Jaakkola, DiJia Su, Bo Liu, Feiyu Chen, Chenyu Wang, Shannon Zejiang Shen, Sid Wang, Siyan Zhao, Song Jiang, Yuandong Tian

October 13, 2025

Yuandong Tian

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

Research Areas

Computer Vision

Core Machine Learning

Natural Language Processing (NLP)

Reinforcement Learning

Systems Research

Theory

Yuandong's Work

ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

darkforestGO Github Repository

FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

Yuandong's Publications

REINFORCEMENT LEARNING

RESEARCH

SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models

CORE MACHINE LEARNING

Deep Think with Confidence

CORE MACHINE LEARNING

Contrastive Predict-and-Search for Mixed Integer Linear Programs

CORE MACHINE LEARNING

GenCO: Generating Diverse Designs with Combinatorial Constraints

CORE MACHINE LEARNING

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

SYSTEMS RESEARCH

Learning Compiler Pass Orders using Coreset and Normalized Value Prediction

CORE MACHINE LEARNING

SYSTEMS RESEARCH

Latent Execution for Neural Program Synthesis

RESEARCH

Understanding Deep Contrastive Learning via Coordinate-wise Optimization

On the Importance of Asymmetry for Siamese Representation Learning

Denoised MDPs: Learning World Models Better Than the World Itself

REINFORCEMENT LEARNING

CORE MACHINE LEARNING

Learning Search Space Partition for Path Planning

CORE MACHINE LEARNING

SYSTEMS RESEARCH

Latent Execution for Neural Program Synthesis

REINFORCEMENT LEARNING

NovelD: A Simple yet Effective Exploration Criterion

REINFORCEMENT LEARNING

MADE: Exploration via Maximizing Deviation from Explored Regions

REINFORCEMENT LEARNING

SYSTEMS RESEARCH

Coda: An End-to-End Neural Program Decompiler

REINFORCEMENT LEARNING

CORE MACHINE LEARNING

Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search

ML APPLICATIONS

Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction

RESEARCH

COMPUTER VISION

One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers

ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

RESEARCH

Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees

RESEARCH

COMPUTER VISION

M3RL: MIND-AWARE MULTI-AGENT MANAGEMENT REINFORCEMENT LEARNING