Related papers: Model of the Weak Reset Process in HfOx Resistive …
Resistance-change random access memory (RRAM) devices are nanoscale metal-insulator-metal structures that can store information in their resistance states, namely the high resistance (HRS) and low resistance (LRS) states. They are a…
Training machine learning models on mobile devices has the potential of improving both privacy and accuracy of the models. However, one of the major obstacles to achieving this goal is the memory limitation of mobile devices. Reducing…
Fine-tuning large language models on new data improves task performance but degrades capabilities learned during pretraining, a phenomenon known as catastrophic forgetting. Existing methods mitigate this by modifying the fine-tuning…
Weak memory models are a consequence of the desire on part of architects to preserve all the uniprocessor optimizations while building a shared memory multiprocessor. The efforts to formalize weak memory models of ARM and POWER over the…
Deep reinforcement learning algorithms are usually impeded by sampling inefficiency, heavily depending on multiple interactions with the environment to acquire accurate decision-making capabilities. In contrast, humans rely on their…
We apply reduced-order modeling (ROM) techniques to single-phase flow in faulted porous media, accounting for changing rock properties and fault geometry variations using a radial basis function mesh deformation method. This approach…
With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks against adversarial examples, imperceptibly perturbed inputs that…
Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…
We propose an axiomatic generic framework for modelling weak memory. We show how to instantiate this framework for SC, TSO, C++ restricted to release-acquire atomics, and Power. For Power, we compare our model to a preceding operational…
Modern processors deploy a variety of weak memory models, which for efficiency reasons may execute instructions in an order different to that specified by the program text. The consequences of instruction reordering can be complex and…
Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be…
The growing energy demands of information and communication technologies, driven by data-intensive computing and the von Neumann bottleneck, underscore the need for energy-efficient alternatives. Resistive random-access memory (RRAM)…
A significant performance reduction is often observed in speech recognition when the rate of speech (ROS) is too low or too high. Most of present approaches to addressing the ROS variation focus on the change of speech signals in dynamic…
The memory model for RISC-V, a newly developed open source ISA, has not been finalized yet and thus, offers an opportunity to evaluate existing memory models. We believe RISC-V should not adopt the memory models of POWER or ARM, because…
Understanding the resistive switching behavior, or the resistance change, of oxide-based memristor devices, is critical to predicting their responses with known electrical inputs. Also, with the known electrical response of a memristor, one…
Memristive devices have shown great promise to facilitate the acceleration and improve the power efficiency of Deep Learning (DL) systems. Crossbar architectures constructed using these Resistive Random-Access Memory (RRAM) devices can be…
This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without…
Deep neural receivers (NeuralRxs) for Orthogonal Frequency Division Multiplexing (OFDM) signals are proposed for enhanced decoding performance compared to their signal-processing based counterparts. However, the existing architectures…
Resistive memory is a promising alternative to SRAM, but is also an inherently unstable device that requires substantial effort to ensure correct read and write operations. To avoid the associated costs in terms of area, time and energy,…
The parameter-efficient fine-tuning paradigm has garnered significant attention with the advancement of foundation models. Although numerous methods have been proposed to reduce the number of trainable parameters, their substantial memory…