Bin Gu

Why Variance Reduction Hurts Noisy Zeroth-Order Hard-Thresholding?

S$^2$MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

Distribution-Aware Multi-Granularity Phase Coding: Towards Lower Conversion Error for Spike-Driven Large Language Models

Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward Passes

Online Black-Box Prompt Optimization with Regret Guarantees under Noisy Feedback

Achieve Latency-Efficient Tempora-Coding Spiking LLMs via Discretization-Aware Conversion

How to Get Spiking LLMs? A Dual ANN-to-SNN Conversion with Layer-Wise Calibration

Silver Stepsize for Faster Zeroth-Order Optimization

EasySpiking: Spike-Friendly Function Approximations for Spiking LLMs Without Fine-Tuning

Event-Driven Online Vertical Federated Learning

FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning

Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies

Improving Generalization and Robustness in SNNs Through Signed Rate Encoding and Sparse Encoding Attacks

Collaborative Discrete-Continuous Black-Box Prompt Learning for Language Models

Dual Variance Reduction with Momentum for Imbalanced Black-Box Discrete Prompt Learning

Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons

Temporal Misinformation and Conversion through Probabilistic Spiking Neurons

SPACT18: Spiking Human Action Recognition Benchmark Dataset with Complementary RGB and Thermal Modalities

FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning

S$^2$MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees

Accelerate Vertical Federated Adversarial Learning with Dual-level Decoupled Backpropagation

Query Efficient Nonsmooth Stochastic Black-Box Bilevel Optimization with Bregman Distance

Fight Fire with Fire: Multi-biased Interactions in Hard-Thresholding

Overcoming Missing Label Vocabulary in Black-Box Discrete Prompt Learning

From Conflicts to Convergence: A Zeroth-order Method for Multi-Objective Learning