1. A Universal Law of Robustness via Isoperimetry
2. On the Expressivity of Markov Reward
3. Deep Reinforcement Learning at the Edge of the Statistical Precipice
4. MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers
: measuring how close mahcine-generated text is to human language is an important issue. MAUVE identifies known properties of generated text and scales naturally with model size.
5. Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms
6. Moser Flow: Divergence-based Generative Modeling on Manifolds
NLP Researcher : https://hyukhunkoh-ai.github.io/