12 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…
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…
ZO-SAM: Zero-Order Sharpness-Aware Minimization for Efficient Sparse Training
Jie Ji, Gen Li, Kaiyuan Deng +2
Deep learning models, despite their impressive achievements, suffer from high computational costs and memory requirements, limiting their usability in resource-constrained environm…
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…
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…
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…
Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
Mingyu Cao, Gen Li, Jie Ji +6
Mixture-of-Experts (MoE) has garnered significant attention for its ability to scale up neural networks while utilizing the same or even fewer active parameters. However, MoE does…
Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design
Gen Li, Zhihao Shu, Jie Ji +4
Deep neural networks (DNNs) are frequently employed in a variety of computer vision applications. Nowadays, an emerging trend in the current video distribution system is to take ad…