Cong Shen

Training-Free Speedup for Retrieval-Augmented Generation with Staged Parallel Speculation

Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits

Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning

Spectrum Intelligence via Multi-Agent Hybrid Retrieval-Augmented Generation

On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery

Greedy Sampling Is Provably Efficient For RLHF

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning

A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization

On the Training Convergence of Transformers for In-Context Classification

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures

Neighborhood and Global Perturbations Supported SAM in Federated Learning: From Local Tweaks To Global Awareness

Channel-Wise Mixed-Precision Quantization for Large Language Models