Isadora White

Hi! I am a PhD Student at UC San Diego. Previously, I did my undergrad at UC Berkeley in Computer Science and was advised by Sergey Levine.


Currently, I am excited about:

  • Human-language agent interaction I am excited about agents that learn through interaction to collaborate with humans, by being honest and helpful.
  • Codebase Understaning agents that can understand complex codebases and solve bugs
  • Multi-agent Reinforcement Learning agents that can learn from multi-turn interactions with humans and other agents
  • Multi-agent Systems Creating models that can work efficiently with other agents to achieve comoplex objectives.
Reach out if you are interested in collaborating!

Email  /  CV  /  Twitter  /  Github

profile photo

Research & Projects

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
ICML 2025
paper / website

Created benchmarks to test the capabilities of multi-turn RL algorithms in language.

Communicate to Play: Pragmatic Reasoning for Efficient Cross-Cultural Communication `
Isadora White , Sashrika Pandey, Michelle Pan
EMNNLP Findings 2024 , Aug. 2024
paper / code

Analyzed the game Codenames to understand how players use language to communicate efficiently across cultures and developed a method to allow players to communicate more efficiently across cultures.

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