Projects
Things I do, including research, engineering projects, and miscellaneous interests.
Research
Research publications for AI Agent, RL, Causality and Interpretability.
A Benchmark for Characterizing Errors in Tool-Use LLMs
arXiv, 2024
Unlocking Latent Reasoning Capabilities via Self-Rewarding
arXiv, 2024
Optimizing Principled Reasoning and Acting of LLM Agent
CoNLL, 2024
World's Best Open-Source Model for Function-Calling
arXiv, 2024
AI Software Engineer with 55% resolve rate on SWE-Bench Lite
ICLR, 2025
Sythetic Data Pipeline for Generating Verifiable and Diverse Function-Calling Datasets
NeurIPS, 2024
Generative Critic Model Optimized for Self-Reflection and Reasoning Capabilities of AI Agents
ICLR, 2024
Unified Data and Training Pipeline for Effective Agent Learning
arXiv, 2024
Salesforce's In-House Library for Multi-Agent Orchestration and Reasoning
arXiv, 2024
A Fast and Interpretable Localization Method for LLM Editing
arXiv, 2024
Causal Layering via Conditional Entropy
CLeaR, 2024
Learning Temporal Causal Representation under Non-Invertible Generation Process
ICML, 2024
Personalized Recommender Systems Using LLM
arXiv, 2023
Temporally Disentangled Representation Learning under Unknown Nonstationarity
NeurIPS, 2023
Unified Benchmarks for Orchestrating Language Agents
ICLR, 2024
Monte Carlo Tree Search with UCB Memory for AI Agents
ICLR, 2024
Causal Discovery Suffers from Low Precision on All but Extremely Sparse Graphs
PGM, 2024
Non-Parametric State-Space Models
OpenReview, 2023
Prompt Learning with Optimal Transport for Vision-Language Models
ICLR, 2023
Salesforce Library for for Fast and Scalable Causal Reasoning
arXiv, 2023
ML Battery Safety Risk Level Classification Model
Journal of Power Sources, 2022
Temporally Disentangled Representation Learning
NeurIPS, 2022
Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Driving
ICML, 2022
How Do New Transit Stations Affect People's Sentiment and Activity?
Transport Policy, 2022
Multi-Source Domain Adaptation with Minimal Change Principle
ICML, 2022
Tool for Recovering Causal Concepts and Relations from Videos
ICLR, 2022
Data-Driven Safety Risk Prediction of Lithium-Ion Battery
Advanced Energy Materials, 2021
Next-Day Morning Traffic Prediction Using Social Media Data
TRC, 2021
Distributed RL for Demand Flexibility in Thermostatically Controlled Loads
SmartGridComm, 2020
Recommending Signal Plans under Incidents with Real-Time Traffic
TRR, 2020
Condition Monitoring of Wheel Wear for High-Speed Trains
PHM, 2018
Engineering
Innovative AI systems and products I’ve developed and deployed at scale.
Scalable Collaboration for Multiple AI Agents in Workspaces
Jan 2024 – Present
Enhancing IDE Productivity through AI Code Planning, Editing, and Execution
Aug 2024 – Present
AIOps Augments SREs' Capabilities for Automating Operations
Jan 2023 – Dec 2023
