Hui Liu

15

Papers

111

Total Citations

Papers (15)

Catastrophic Failure of LLM Unlearning via Quantization

SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures

Memory Injection Attacks on LLM Agents via Query-Only Interaction

NeurIPS 2025arXiv

Unlocking Efficient, Scalable, and Continual Knowledge Editing with Basis-Level Representation Fine-Tuning

AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

NeurIPS 2025arXiv

Towards Calibrated Deep Clustering Network

Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models

Learning Cross-Domain Representations for Transferable Drug Perturbations on Single-Cell Transcriptional Responses

Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression

Test-time Adaptation for Foundation Medical Segmentation Model Without Parametric Updates

T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Large Language Model Signals for Science Question Answering

Syntax-Aware Network for Handwritten Mathematical Expression Recognition

Semantic-Embedded Unsupervised Spectral Reconstruction From Single RGB Images in the Wild

Learning Dynamic Interpolation for Extremely Sparse Light Fields With Wide Baselines

ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction