Qiuyi Zhang

Randomization Boosts KV Caching, Learning Balances Query Load: A Joint Perspective

Provable Distributional Value Iteration under Partial Observability

Beyond Worst-Case Dimensionality Reduction for Sparse Vectors

Formalizing Spuriousness of Biased Datasets using Partial Information Decomposition

Predicting from Strings: Language Model Embeddings for Bayesian Optimization