Isadora White
Hi! I am first-year PhD Student at UCSD advised by Prithviraj Ammanabrolu and Lianhui Qin. Previously, I did my undergrad at UC Berkeley in Computer Science and
was advised by Sergey Levine.
Within the intersection of Natural Language Processing and Reinforcement Learning I am interested in the following topics:
- Human-language agent interaction I am excited about agents that learn through interaction to collaborate with humans, by being honest and helpful.
- Commonsense Reasoning agents that can reason about the world and make deductions
Beyond this, I am interested in developing more efficient open-source models and developing models that can have real-world impact. Reach out if you are interested in collaborating!
Email /
CV /
Twitter /
Github
|
|
Communicate to Play: Pragmatic Reasoning for Efficient Cross-Cultural Communication
`
Isadora White ,
Sashrika Pandey,
Michelle Pan
EMNNLP Findings 2024 , Aug. 2024
paper
/
code
Propose a method for cross-cultural communication in the game of Codenames.
|
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Marwa Abdulhai
Isadora White ,
Charlie Snell,
Charles Sun,
Joey Hong ,
Yuexiang (Simon) Zhai ,
Kelvin Xu
Sergey Levine
Large Models in Decision Making Workshop at ICLR, In Submission as Conference Paper , Nov. 2023
paper
/
website
Created benchmarks to test the capabilities of multi-turn RL algorithms in language.
|
Deep Learning Methods for Movement Classification and Artifact Correction for Reliable Brain-Computer Interfaces
Annie Taylor,
Isadora White ,
Zheyuan Hu
Shiangyi Lin
Deep Learning Course Research Project, May 2023
report
We explore new deep-learning architectures involving transformers and CNNs for classifying ECoG signals as robotic motion.
We propose data imputation and a transformer encoder/decoder architecture to correct artifacts.
|
Reward and Exploration Strategies for Wordle with Deep Reinforcement Learning
Isadora White, Bennett Cohen, Sean Tsung
Deep Reinforcement Learning Course Project, Dec. 2022
report
/
code
Trained Deep Reinforcement Learning agents to play Wordle with custom reward functions and exploration algorithms.
|
Moderat: Language Models for Fair and Explainable German Comment Moderation
Isadora White,
Kilian Mueller
DAAD RISE Germany Internship Presentation, Aug. 2022
slides
/
code
Compared fine-tuned multi-lingual and single language LMs for hate speech detection, explained predictions using SHAP values, and mitgated biases.
|
Website template from Jon Barron
|