23 papers
Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning
Yang Xiao, Kaiyuan Deng, Gen Li +4
Diffusion models pose significant risks regarding the generation of illicit content and copyright violations. This has catalyzed the development of machine unlearning to erase harm…
Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models
Kaiyuan Deng, Yuchen Li, Yang Xiao +3
Existing attacks on unlearned diffusion models assume that the erased concepts are known in advance and focus on recovering them. In practice, however, model providers may not disc…
No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models
Kaiyuan Deng, Yuchen Li, Gen Li +5
Text-to-image diffusion models can generate prohibited content, which motivates concept erasure through machine unlearning. Most erasure methods intervene at the text interface, th…
Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents
Le Chen, Zishen Wan, Baixi Sun +6
Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles and exhibit different size, re…
Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages
Chih-Hsuan Yang, Anjir Ahmed Chowdhury, Cheng-Hau Yang +7
Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likel…
HPD-Parsing: Hierarchical Parallel Document Parsing
Shu Wei, Jingjing Wu, Lingshu Zhang +10
Efficient teamwork typically combines global coordination with parallel execution, a principle not yet fully reflected in unified Vision-Language Model (VLM)-based document parsers…
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Jiajie Jin, Yuyang Hu, Kai Qiu +15
Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the result…
PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
Anjir Ahmed Chowdhury, Syed Zawad, Xiaolong Ma +2
Parameter-Efficient Fine-Tuning (PEFT) is widely used for adapting Large Language Models (LLMs) for various tasks. Recently, there has been an increasing demand for fine-tuning a s…
Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation
Yang Xiao, Huiyuan Chen, Kaiyuan Deng +6
We propose \textbf{Compressed Video Aggregator} (CVA), a lightweight micro-video recommendation module that decouples video information from preference learning. CVA first summariz…
Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models
Ci Zhang, Zhaojun Ding, Chence Yang +7
Pruning-based unlearning has recently emerged as a fast, training-free, and data-independent approach to remove undesired concepts from diffusion models. It promises high efficienc…
Your Language Model Secretly Contains Personality Subnetworks
Ruimeng Ye, Zihan Wang, Zinan Ling +4
Humans shift between different personas depending on social context. Large Language Models (LLMs) demonstrate a similar flexibility in adopting different personas and behaviors. Ex…
Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
Kaiyuan Deng, Bo Hui, Gen Li +4
The widespread adoption of text-to-image (T2I) diffusion models has raised concerns about their potential to generate copyrighted, inappropriate, or sensitive imagery. As a practic…
Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
Kaiyuan Deng, Gen Li, Yang Xiao +2
Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into machine unlearning. However, extending…
From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs
Kaiyuan Deng, Hangyu Zheng, Minghai Qing +11
Deploying models, especially large language models (LLMs), is becoming increasingly attractive to a broader user base, including those without specialized expertise. However, due t…
LightCache: Memory-Efficient, Training-Free Acceleration for Video Generation
Yang Xiao, Gen Li, Kaiyuan Deng +5
Training-free acceleration has emerged as an advanced research area in video generation based on diffusion models. The redundancy of latents in diffusion model inference provides a…
Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks
Gaurav Bagwe, Saket S. Chaturvedi, Xiaolong Ma +3
Retrieval-augmented generation (RAG) enhances factual grounding by integrating retrieval mechanisms with generative models but introduces new attack surfaces, particularly through…
Efficient Knowledge Graph Unlearning with Zeroth-order Information
Yang Xiao, Ruimeng Ye, Bohan Liu +2
Due to regulations like the Right to be Forgotten, there is growing demand for removing training data and its influence from models. Since full retraining is costly, various machin…
The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models
Yang Xiao, Gen Li, Jie Ji +3
Machine unlearning aims to efficiently eliminate the memory about deleted data from trained models and address the right to be forgotten. Despite the success of existing unlearning…
What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale
Xiaoyong Yuan, Xiaolong Ma, Linke Guo +1
Diffusion models (DMs) have revolutionized text-to-image generation, enabling the creation of highly realistic and customized images from text prompts. With the rise of parameter-e…
Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization
Gen Li, Yang Xiao, Jie Ji +4
Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowle…
Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Information Processing
Yang Xiao, Wang Lu, Jie Ji +4
The design of artificial neural networks (ANNs) is inspired by the structure of the human brain, and in turn, ANNs offer a potential means to interpret and understand brain signals…
Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
Qitao Tan, Jun Liu, Zheng Zhan +6
Large language models (LLMs) excel across various tasks, but standard first-order (FO) fine-tuning demands considerable memory, significantly limiting real-world deployment. Recent…
DBA-DFL: Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learning
Bohan Liu, Yang Xiao, Ruimeng Ye +3
Distributed backdoor attacks (DBA) have shown a higher attack success rate than centralized attacks in centralized federated learning (FL). However, it has not been investigated in…