Qixin Zhang

Researcher@Nanyang Technological University·新加坡·OpenReview

研究方向

Spiking Neural Networks · Combinatorial Optimization · Network Pruning · Subset Selection · Data Market · Submodular Optimization · Revenue Management · Influence Maximization

Qixin Zhang

Convergent Differential Privacy Analysis for General Federated Learning

Sample Lottery: Unsupervised Discovery of Critical Instances for LLM Reasoning

MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs

GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks

Fractional-Order Spiking Neural Network

Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks

TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs

DREAM: Decoupled Reinforcement Learning with Reward Measurement for Large Language Model Test-time Training

SeWA: Selective Weight Average via Probabilistic Masking

Self-Reflective Generation at Test Time

Minutes to Converage: Dataset Distillation for Rapid SNN Training on Event Streams

Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs

Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives

Refining Adaptive Zeroth-Order Optimization at Ease

Convergent Differential Privacy Analysis for General Federated Learning

Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency

Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints

Contextual Bandits for Unbounded Context Distributions

Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes