相关论文: BARRIER: Bounded Activation Regions for Robust Inf…

The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer…

Machine unlearning aims to remove specific knowledge (e.g., copyrighted or private data) from a trained model without full retraining. In practice, models are often quantized (e.g., 4-bit) for deployment, but we find that quantization can…

Machine unlearning (MU) aims to efficiently remove sensitive or harmful memory from a pre-trained model. The key challenge is to balance the potential tradeoff between unlearning efficacy and utility preservation, which involves forgetting…

The ability of deep neural networks to continually learn and adapt to a sequence of tasks has remained challenging due to catastrophic forgetting of previously learned tasks. Humans, on the other hand, have a remarkable ability to acquire,…

Continual learning under adversarial conditions remains an open problem, as existing methods often compromise either robustness, scalability, or both. We propose a novel framework that integrates Interval Bound Propagation (IBP) with a…

Machine unlearning for LLMs aims to remove sensitive or copyrighted data from trained models. However, the true efficacy of current unlearning methods remains uncertain. Standard evaluation metrics rely on benign queries that often mistake…

Recent generative models face significant risks of producing harmful content, which has underscored the importance of machine unlearning (MU) as a critical technique for eliminating the influence of undesired data. However, existing MU…

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…

Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspective for MU is presented upon low-dimensional feature…

Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting. We propose CRAFT, a continual learning framework that avoids updating model weights by instead…

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Binary Neural Networks (BNNs), which constrain both weights and activations to binary values, offer substantial reductions in computational complexity, memory footprint, and energy consumption. These advantages make them particularly well…

Machine unlearning seeks to remove the influence of particular data or class from trained models to meet privacy, legal, or ethical requirements. Existing unlearning methods tend to forget shallowly: phenomenon of an unlearned model pretend…

Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack…

The rapid advancement of text-to-image Diffusion Models has led to their widespread public accessibility. However these models, trained on large internet datasets, can sometimes generate undesirable outputs. To mitigate this, approximate…

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to…

Machine unlearning is an emerging technique that aims to remove the influence of specific data from trained models, thereby enhancing privacy protection. However, recent research has uncovered critical privacy vulnerabilities, showing that…

Scaling data and models has played a pivotal role in the remarkable progress of computer vision and language. Inspired by these domains, recent efforts in robotics have similarly focused on scaling both data and model size to develop more…

While Multimodal Large Language Models (MLLMs) are increasingly integrated with Retrieval-Augmented Generation (RAG) to mitigate hallucinations, the introduction of external documents can conceal severe failure modes at the instance level.…