Experience

  1. Amazon logo

    Applied Scientist Intern

    Amazon
    • Develop a unified agentic framework based on diffusion language models (dLMs) for task completion and world modeling.
    • Mentor: Anwesan Pal. Manager: Narayanan Sadagopan.
  2. Waymo logo

    Ph.D. Research Intern

    Waymo
    • Perception Team. Developed a unified VLM for autonomous driving perception (patent application pending) that learns dense metric scene geometry and sensor-grounded spatial reasoning from camera observations and sparse LiDAR.
    • Built core perceptual capabilities for vision-language-action (VLA) systems — dense depth, object-centric distance, driving relevance, depth ordering, and time-to-reach reasoning — through a shared geometry-language scene representation.
    • Mentors: Mayank Singal, Prasanna Krishnasamy. Managers: Ming Zou, Christian Lauterbach.
  3. J.P. Morgan AI Research logo

    Research Scientist Intern

    J.P. Morgan AI Research
    • Led SlideAgent, a hierarchical agentic framework for multi-page visual document understanding (ACL 2026 main).
    • Built MLLM-based agentic pipelines for parsing high-resolution slide decks and financial reports, integrating context compression and retrieval-augmented generation.
    • Mentors: Rachneet Kaur, Zhen Zeng. Managers: Sumitra Ganesh, Manuela Veloso.
  4. Visa Research logo

    Research Collaborator (Visa Research Grant)

    Visa Research
    • Led SARA, a selective and adaptive RAG framework with context compression (ACL 2026 main).
    • Developed a hybrid compression strategy combining fine-grained spans with compact semantic vectors, achieving consistent gains across Mistral, Llama, and Gemma.
    • Mentors: Vineeth Rakesh Mohan, Yingtong Dou, Menghai Pan. Manager: Mahashweta Das.
  5. Adobe Research logo

    Research Scientist Intern

    Adobe Research
    • Built ScreenLLM, a multimodal LLM for GUI understanding and action prediction (WebConf'25 MM4SG Workshop).
    • Designed a stateful screen schema that summarizes dynamic UI sessions as time-aware textual context, plus a key-frame extractor for significant UI transitions.
    • Mentors: Gang Wu, Yu Shen, Stefano Petrangeli. Managers: Saayan Mitra, Vishy Swaminathan.
  6. Microsoft Research Asia (Social Computing Group) logo

    Research Scientist Intern

    Microsoft Research Asia (Social Computing Group)
    • Mentors: Xiting Wang, Jindong Wang, Xing Xie.
    • Published papers across LLMs (ICML'24, ICML'23, AAAI'23), LLM agents (EMNLP'24, ICML'24), misinformation detection (KDD'22, AAAI'22), few-shot learning (ACL'24, AAAI'23), and explainable AI (AAAI'22).
    • Received Microsoft Research “Star of Tomorrow” Award (2021).
  7. Amazon (Fulfillment By Amazon) logo

    Software Engineer Intern

    Amazon (Fulfillment By Amazon)
    • Designed and implemented IAR Manual Analysis, a scalable workflow on AWS Step Functions and Lambda that automates aggregation of S3 and DynamoDB data for SageMaker training, handling >16k requests per summary stage.
    • Deployed the workflow across all AWS regions (EU/FE/NA) via CloudFormation; built DataCraft pipeline for ingesting DynamoDB tables into the Andes catalog.
  8. IBM China Development Laboratories logo

    Software Engineer Intern

    IBM China Development Laboratories
    • Built Compass DataRouter (Go + MongoDB) for the Compass project, reducing memory usage and accelerating data retrieval.
    • Improved the Compass monitoring dashboard with React.js.

Education

  1. Georgia Institute of Technology (Georgia Tech) logo

    Ph.D. in Computer Science

    Georgia Institute of Technology (Georgia Tech)
    • Advisor: Prof. Srijan Kumar.
    • Research on multimodal foundation models, world models and spatial reasoning, LLM agents and multi-agent systems, and post-training and self-improvement.
    • Publications include EMNLP'26, ACL'26, ICLR'26, ICWSM'26, EMNLP'25, ACL'25, WebConf'24, ACL'24, KDD'23, CIKM'24, AAAI'23.
    • GPA: 4.0/4.0.
  2. University of California, Los Angeles (UCLA) logo

    B.S. in Computer Science

    University of California, Los Angeles (UCLA)
    • Advisors: Prof. Yizhou Sun, Prof. Wei Wang.
    • Published 4 papers at top-tier ML and data mining venues (AAAI, KDD, Web Conference). Continuing collaborator on LLMs and graph neural networks (GNNs) (EMNLP'25, WebConf'23).
    • GPA: 3.82/4.0. Dean’s Honor List (5 times).
Skills & Hobbies
Research Areas
Vision-Language & Multimodal Models
World Models, Embodied AI & Spatial Reasoning
LLM Agents & Multi-Agent Systems
Post-training, RL & Self-Improvement
Hobbies
Rabbit
Photography
Hiking
Awards
MLCommons ML and Systems Rising Stars
MLCommons ∙ January 2026
Recognized among rising stars in ML and systems research.
Best Paper Award at Good-Data @ AAAI 2025 Workshop
AAAI Conference ∙ March 2025
SciEvo received Best Paper (2 of 25 accepted) at the Good-Data @ AAAI 2025 Workshop.
Roblox Graduate Fellowship Finalist
Roblox Corporation ∙ December 2024
Selected as finalist for the Roblox Graduate Fellowship supporting research in AI and gaming.
AAAI Student Scholarship (3 times)
AAAI Conference ∙ March 2025
Student scholarships at AAAI 2022, 2023, and 2025.
Microsoft Research “Star of Tomorrow” Award of Excellence
Microsoft Research ∙ June 2021
Awarded for research contributions during internship at Microsoft Research Asia.
UCLA Dean’s Honor List for Superior Academic Achievement (5 times)
UCLA ∙ December 2021
Dean’s Honor List in Spring 2019, Winter 2020, Spring 2020, Winter 2021, and Spring 2021.
Languages
100%
English
100%
Chinese
25%
Japanese