top of page
e77053_1ccff4b3974a445bb15090145aab86e5~mv2.jpg

Conferences / Preprints
(* equal contribution)

Presentations / Talks

Hi! I am Yanhong Li, a final-year undergraduate at the University of Chicago. I am broadly interested in natural language processing and multimodal learning. My current projects are centered around retrieval-augmented language models, and I'm still in the process of exploring.​

I am extremely grateful to work with Prof. David McAllester (TTIC), Prof. Karen Livescu (TTIC), Prof. Michael Maire (UChicago), and Prof. Jiawei Zhou (Stony Brook). In the past, I've worked with Prof. Allyson Ettinger (Ai2). I couldn’t appreciate their invaluable insights and support more!​

Also, I would like to say a huge thank you to all my wonderful mentors/collaborators: David Yunis @TTIC, Chenghao Yang @UChicago, Marcelo Sandoval-Castañeda @TTIC. Check out their interesting work!​!

 

I always love to chat about research: yanhongli@uchicago.edu

Yanhong Li, Karen Livescu, Jiawei Zhou. Chunk-Distilled Language Modeling. In submission. 

Yanhong Li, David Yunis, David McAllester, Jiawei Zhou. Context-Efficient Retrieval with Factual Decomposition. In submission.

Ming Li, Yanhong Li, Tianyi Zhou. What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective. In submission. 

 

Yanhong Li*, Chenghao Yang*, Allyson Ettinger. When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models. NAACL 2024 Findings.


Marcelo Sandoval-Castaneda, Yanhong Li, Bowen Shi, Diane Brentari, Karen Livescu, and Gregory Shakhnarovich. TTIC’s Submission to WMT-SLT 23. WMT 2023.
(Top-performing system in challenge)


Marcelo Sandoval-Castaneda, Yanhong Li, Diane Brentari, Karen Livescu, Gregory Shakhnarovich. Self-Supervised Video Transformers for Isolated Sign Language Recognition. Arxiv.

Convolutional Knowledge Graph Link Prediction with Reshaped Embeddings, The Undergraduate Consortium at SIGKDD 2023

bottom of page