πAbout Me
Helloπ! I am Yiqiao Jin (ι³θ½ΆδΉ, Ahren), a Computer Science Ph.D. candidate at Georgia Tech, advised by Prof. Srijan Kumar.
My research develops adaptive and efficient AI systems, with a focus on LLM agents, agent memory, self-distillation, multimodal LLMs, and structured multi-agent intelligence. My work has appeared at ACL, EMNLP, ICML, NeurIPS, ICLR, KDD, AAAI, CIKM, and The Web Conference, including several oral presentations.
I am currently a Ph.D. Intern on the Perception team at Waymo, working on VLM-based metric depth estimation and spatial reasoning for autonomous driving. During my Ph.D., I have also interned or collaborated with J.P. Morgan AI Research (SlideAgent), Visa Research (SARA), Adobe Research (ScreenLLM), and Microsoft Research Asia (FinerFact, Prototypical Fine-tuning, CompeteAI, AgentReview). Before Georgia Tech, I worked with Prof. Yizhou Sun and Prof. Wei Wang at the UCLA Scalable Analytics Institute (ScAi).
Selected honors include the MLCommons ML and Systems Rising Stars (2026), Best Paper Award at Good-Data @ AAAI 2025 Workshop, Roblox Graduate Fellowship Finalist (2024), and the Microsoft Research “Star of Tomorrow” Award. My work on cross-lingual LLM evaluation has been featured by Scientific American, The World, and Georgia Tech News.
- Large Language Models (LLMs)
- LLM Agents & Agent Memory
- Multi-Agent Systems (MAS)
- Self-Distillation & Efficient LLM Adaptation
- Multimodal LLMs & Visual Document Understanding
- Graph Neural Networks & Temporal Graphs
Ph.D. in Computer Science
Georgia Institute of Technology (Georgia Tech)
B.S. in Computer Science
University of California, Los Angeles (UCLA)
Experience
Ph.D. Research Intern
Waymo- Perception Team. Develop VLM-based metric depth estimation models for autonomous driving, enabling point-level and object-centric distance prediction from camera/video inputs and scene metadata.
- Build data generation and evaluation pipelines for spatial reasoning tasks (absolute depth prediction, relative depth comparison, temporal depth consistency).
- Mentors: Mayank Singal, Prasanna Krishnasamy. Manager: Ming Zou.
Graduate Research Assistant
Georgia Institute of TechnologyAdvisor: Prof. Srijan Kumar. Research on LLM agents, agent memory, multimodal LLMs, self-distillation, and graph mining. Publications include ACL'26, ICLR'26, ICWSM'26, EMNLP'25, ACL'25, WebConf'24, ACL'24, KDD'23, CIKM'24.
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.
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.
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.
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).
Undergraduate Research Assistant
UCLA Scalable Analytics Institute (ScAi)- Advisors: Prof. Yizhou Sun, Prof. Wei Wang.
- Continuing collaborator on graph neural networks, code recommendation, and protein/biology-focused LLMs (EMNLP'25, WebConf'23).
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.
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
Ph.D. in Computer Science
Georgia Institute of Technology (Georgia Tech)Advised by Prof. Srijan Kumar. Research focus on LLM agents, agent memory, multimodal LLMs, and efficient LLM adaptation. GPA: 4.0/4.0.B.S. in Computer Science
University of California, Los Angeles (UCLA)GPA: 3.82/4.0. Published 4 papers (3 first-authored) at top-tier ML and data mining venues (AAAI, KDD, Web Conference). Dean’s Honor List (5 times).
π Location
Atlanta, GA / Beijing, China
π§ Email
yjin328[AT]gatech.edu
π’ Office
756 W Peachtree St NW, Atlanta, GA 30308
CODA 13th Floor
π Office Hours
Monday - Sunday 9:00 to 20:00