106 citations · 377 across the 79 of their papers we have counts for
81 papers
InjecMEM: Memory Injection Attack on LLM Agent Memory Systems
Hanling Tian, Gengyu Zhang, Zeyang Sha +5
Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce…
CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA
Gengyu Zhang, Haiyin Ran, Zhengbao He +4
As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging. Low-Rank Adaptation (LoRA), currently…
Stochastic Optimal Control Sampling for Diffusion Inverse Problems
Jie Zhang, Youmei Qiu, Hanling Tian +3
Benefiting from the strong ability to capture data distributions, diffusion models have become powerful tools for solving image inverse problems. The key is to controllably steer t…
SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector
Jingyuan Zhang, Yucheng Bai, Peixi Wen +6
Large Language Model (LLM) unlearning aims to remove undesirable knowledge or behaviors while preserving retained capabilities. Current unlearning methods all involve a trade-off b…
Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter
Zhengbao He, Ruiqi Ding, Zhehao Huang +3
Low-rank adaptation (LoRA) enables parameter-efficient specialization of foundation models, but the proliferation of task-specific adapters fragments capabilities across many adapt…
A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
Ding Chen, Xinwen Cheng, Xuyang Zhong +3
While Membership Inference Attacks (MIAs) are the prevailing method for identifying training data, their application has expanded into privacy auditing and machine unlearning. Neve…
FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG
Mengzhu Chen, Haodong Yang, Jia Cai +1
Retrieval-Augmented Generation (RAG) systems critically depend on how external knowledge is segmented, structured, and retrieved. Most existing approaches either retrieve fixed-len…
Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information
Xinwen Cheng, Jingyuan Zhang, Zhehao Huang +2
The powerful generative capabilities of diffusion models have raised growing privacy and safety concerns regarding generating sensitive or undesired content. In response, machine u…
RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format
Zhehao Huang, Yuhang Liu, Baijiong Lin +5
Large reasoning models (LRMs) excel at a long chain of reasoning but often fail to faithfully follow instructions regarding output format, constraints, or specific requirements. We…
VL-RouterBench: A Benchmark for Vision-Language Model Routing
Zhehao Huang, Baijiong Lin, Jingyuan Zhang +5
Multi-model routing has evolved from an engineering technique into essential infrastructure, yet existing work lacks a systematic, reproducible benchmark for evaluating vision-lang…
Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
Yuhang Liu, Tao Li, Zhehao Huang +2
Fine-tuning large-scale pre-trained models with limited data presents significant challenges for generalization. While Sharpness-Aware Minimization (SAM) has proven effective in im…
T2I-ConBench: Text-to-Image Benchmark for Continual Post-training
Zhehao Huang, Yuhang Liu, Yixin Lou +7
Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of…
A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning
Zhehao Huang, Xinwen Cheng, Jie Zhang +5
Recent advancements in deep models have highlighted the need for intelligent systems that combine continual learning (CL) for knowledge acquisition with machine unlearning (MU) for…
Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selection and Approximation
Kun Fang, Qinghua Tao, Mingzhen He +6
Out-of-Distribution (OoD) detection is vital for the reliability of deep neural networks, the key of which lies in effectively characterizing the disparities between OoD and In-Dis…
MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes
Ruikai Yang, Mingzhen He, Zhengbao He +2
Machine unlearning (MU) is to make a well-trained model behave as if it had never been trained on specific data. In today's over-parameterized models, dominated by neural networks,…
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
Zhehao Huang, Xinwen Cheng, JingHao Zheng +4
Machine unlearning (MU) has emerged to enhance the privacy and trustworthiness of deep neural networks. Approximate MU is a practical method for large-scale models. Our investigati…
Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape
Tao Li, Zhengbao He, Yujun Li +3
Fine-tuning large-scale pre-trained models is prohibitively expensive in terms of computation and memory costs. Low-Rank Adaptation (LoRA), a popular Parameter-Efficient Fine-Tunin…
Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model
Kun Fang, Zuopeng Yang, Haibo Hu +3
Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.e., In-Distribution (InD), or fro…
Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy
Tao Li, Weisen Jiang, Fanghui Liu +2
Pre-training followed by fine-tuning is widely adopted among practitioners. The performance can be improved by "model soups"~\cite{wortsman2022model} via exploring various hyperpar…
Learning Analysis of Kernel Ridgeless Regression with Asymmetric Kernel Learning
Fan He, Mingzhen He, Lei Shi +2
Ridgeless regression has garnered attention among researchers, particularly in light of the ``Benign Overfitting'' phenomenon, where models interpolating noisy samples demonstrate…
Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection
Yingwen Wu, Ruiji Yu, Xinwen Cheng +2
In the open world, detecting out-of-distribution (OOD) data, whose labels are disjoint with those of in-distribution (ID) samples, is important for reliable deep neural networks (D…
Towards Natural Machine Unlearning
Zhengbao He, Tao Li, Xinwen Cheng +2
Machine unlearning (MU) aims to eliminate information that has been learned from specific training data, namely forgetting data, from a pre-trained model. Currently, the mainstream…
Data Imputation by Pursuing Better Classification: A Supervised Kernel-Based Method
Ruikai Yang, Fan He, Mingzhen He +2
Data imputation, the process of filling in missing feature elements for incomplete data sets, plays a crucial role in data-driven learning. A fundamental belief is that data imputa…
Decentralized Kernel Ridge Regression Based on Data-Dependent Random Feature
Ruikai Yang, Fan He, Mingzhen He +2
Random feature (RF) has been widely used for node consistency in decentralized kernel ridge regression (KRR). Currently, the consistency is guaranteed by imposing constraints on co…