Zhiqiang Shen

Assistant Professor@Mohamed bin Zayed University of Artificial Intelligence·阿联酋·OpenReview

研究方向

MLLMs · LLMs · Vision Transformer · Data Augmentation · Few-shot Learning · Self-supervised Learning · Knowledge Distillation · Efficient Deep Learning · Network Quantization · Network Binarization · Network Pruning/Slimming · Model Compression · Object Detection · Video Captioning

Zhiqiang Shen

OD$^3$: Optimization-free Dataset Distillation for Object Detection

DarwinLM: Evolutionary Structured Pruning of Large Language Model

Attention Is All You Need for KV Cache in Diffusion LLMs

Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift

Dataset Distillation via Committee Voting

ParamAgent: Language Agents with Parametric Knowledge

Time Blindness: Why Video-Language Models Can’t See What Humans Can?

REL-RAG: Relation-Aware Retrieval-Augmented Generation for Generalizable Knowledge Graph Question Answering

Learning Robust Diffusion Models from Imprecise Supervision

BiGain: Unified Token Compression for Joint Generation and Classification

$M-Attack-V2$: Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting

VideoMolmo: Spatio-Temporal Grounding meets Pointing

Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization

$\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models

Pruning Spurious Subgraphs for Graph Out-of-Distribtuion Generalization

M-Attack-V2: Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting

A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1

FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation

Learning Graph Invariance by Harnessing Spuriosity

Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection

OD³: Optimization-free Dataset Distillation for Object Detection

Diversifying Spurious Subgraphs for Graph Out-of-Distribution Generalization