Related papers: DurableUn: Quantization-Induced Recovery Attacks i…

Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…

Deep neural network (DNN) quantization converting floating-point (FP) data in the network to integers (INT) is an effective way to shrink the model size for memory saving and simplify the operations for compute acceleration. Recently,…

Low-bit quantization of network weights and activations can drastically reduce the memory footprint, complexity, energy consumption and latency of Deep Neural Networks (DNNs). However, low-bit quantization can also cause a considerable drop…

Large language models have achieved significant advancements in complex mathematical reasoning benchmarks, such as MATH. However, their substantial computational requirements present challenges for practical deployment. Model quantization…

Post-training quantization (PTQ) is crucial for deploying efficient object detection models, like YOLO, on resource-constrained devices. However, the impact of reduced precision on model robustness to real-world input degradations such as…

Machine unlearning seeks to remove the influence of specified data from a trained model. While the unlearning accuracy provides a widely used metric for assessing unlearning performance, it falls short in assessing the reliability of…

Backpropagation has been the cornerstone of neural network training for decades, yet its inefficiencies in time and energy consumption limit its suitability for resource-constrained edge devices. While low-precision neural network…

We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore…

Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora. However, this poses risk of privacy and copyright violations, highlighting the need for efficient…

The growing number of parameters and computational demands of large language models (LLMs) present significant challenges for their efficient deployment. Recently, there is an increasing interest in quantizing weights to extremely low…

Large-scale recommendation models are currently the dominant workload for many large Internet companies. These recommenders are characterized by massive embedding tables that are sparsely accessed by the index for user and item features.…

Privacy concerns in LLMs have led to the rapidly growing need to enforce a data's "right to be forgotten". Machine unlearning addresses precisely this task, namely the removal of the influence of some specific data, i.e., the forget set,…

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements.…

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

Modular quantum architectures have emerged as a promising approach for scaling quantum computing systems by connecting multiple Quantum Processing Units (QPUs). However, this approach introduces significant challenges due to costly…

The need for machine unlearning is critical for data privacy, yet existing methods often cause Knowledge Contamination by unintentionally damaging related knowledge. Such a degraded model performance after unlearning has been recently…

Deep learning-based image compression (LIC) has achieved state-of-the-art rate-distortion (RD) performance, yet deploying these models on resource-constrained FPGAs remains a major challenge. This work presents a complete, multi-stage…

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Low-bit post-training quantization (PTQ) is a practical route to deploy reasoning-capable LLMs under tight memory and latency budgets, yet it can markedly impair mathematical reasoning (drops up to 69.81% in our harder settings). We address…