Zeyu Zhang

12

Papers

52

Total Citations

Papers (12)

Efficient Learning with Sine-Activated Low-Rank Matrices

MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants

Effective Training Data Synthesis for Improving MLLM Chart Understanding

FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch

OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad

Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization

VehicleMAE: View-asymmetry Mutual Learning for Vehicle Re-identification Pre-training via Masked AutoEncoders

Self-Explainable Graph Transformer for Link Sign Prediction

Reviewing the Forgotten Classes for Domain Adaptation of Black-Box Predictors

Device-Wise Federated Network Pruning