I’m Lily Zhang, a Tech Lead and Research Scientist in the Bay Area, California. My research focus is: post-training and AI training data. I’ve published at CVPR, ICCV, NeurIPS, RAL [1] [2] [3] [4] [5], and gave a keynote at NVIDIA GTC.

At Latitude AI, I build LLMs, multimodal LLMs, and AI agents for physical AI (Modal GTC panel on agentic post-training). Previously, I led applied R&D at Ford Greenfield Labs (2019–2023) on building perception models and AI training data (IROS keynote).

My latest research (colab w AliCloud) reframes feature engineering as agentic code generation, SFT + RL post-trained AI-infra agent deployed at Alibaba Cloud with 91% adoption (poster at NeurIPS 2025 VLM4RWD, oral at DASFAA 2026). Publishing as Xianling Zhang.

AI Research

Find all published research here.

A Constitution-Grid Instrument for Data-Efficient RL Alignment (C-Guard)

Xianling Zhang · COLM 2026 ER

Post-trained safety guard model with RL, automatic synthetic data generation for safety alignment

Paper Blogpost Code Dataset

Eureka: Feature Engineering as Agentic Code Generation

Hangxuan Li, Renjun Jia, Xuezhang Wu, Yunjie Qian, Zeqi Zheng, Xianling Zhang · NeurIPS-W 2025, Proceedings of the 31st International Conference on Database Systems for Advanced Applications (DASFAA 2026, Oral)

SFT + RL post-trained AI-infra agent deployed at Alibaba Cloud: +16% demand fulfillment, 91% ops adoption.

Paper Poster Project Page

Reward Shaping from Failure Taxonomy for RLVR Terminal Environment

Xianling Zhang

Build verifiable failure taxonomy for RL reward shaping in Multi-turns harbor terminal environment.

Blogpost Code (Soon) Data (Soon)

SuperGeneral: Compositional Tool Environments for Long-Horizon Agents

Xianling Zhang

Learn meta skills. Evaluates four frontier models on tool use, composition, and creation on law, consulting, and investment banking domain datasets.

Project Page Code

SIMBAR: Single Image-Based Scene Relighting for Effective Data Augmentation for Automated Driving Vision Tasks

Xianling Zhang, Nathan Tseng, Ameerah Syed, Rohan Bhasin, Nikita Jaipuria · Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Project Page Paper

Deflating Dataset Bias Using Synthetic Data Augmentation

Nikita Jaipuria, Xianling Zhang, R Bhasin, M Arafa, P Chakravarty, S Shrivastava, S Manglani, VN Murali · Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020

Paper

Advisory Boards

Industry Advisory Board, Texas A&M University

Robotics / MXET program.

Board Meeting

Industry Advisory Board, University of Delaware

Supporting young researchers and shaping strategic directions for the CAR Robotics Lab.

Guest Editor, ACM Transactions on Internet of Things

Autonomous Driving special issue.

Call for Papers