Jingzhao Zhang

Faster Gradient Methods for Highly-smooth Stochastic Bilevel Optimization

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation

Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database

PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning

Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control

Second-Order Min-Max Optimization with Lazy Hessians

Data Mixing Can Induce Phase Transitions in Knowledge Acquisition

Towards Black-Box Membership Inference Attack for Diffusion Models

From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency

Scalable Model Merging with Progressive Layer-wise Distillation

Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?

Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control

Towards Black-Box Membership Inference Attack for Diffusion Models

Understanding Nonlinear Implicit Bias via Region Counts in Input Space

Understanding Nonlinear Implicit Bias via Region Counts in Input Space