Davoud Ataee Tarzanagh

Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees

Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning

Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning

Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection