Related papers: Mitigating Wordline Crosstalk using Adaptive Trees…
Large Language Models (LLMs) have dramatically advanced AI applications, yet their deployment remains challenging due to their immense inference costs. Recent studies ameliorate the computational costs of LLMs by increasing their activation…
Deep learning has proved successful in many applications but suffers from high computational demands and requires custom accelerators for deployment. Crossbar-based analog in-memory architectures are attractive for acceleration of deep…
Deformable Attention Transformers (DAT) have shown remarkable performance in computer vision tasks by adaptively focusing on informative image regions. However, their data-dependent sampling mechanism introduces irregular memory access…
Rowhammer is a critical vulnerability in dynamic random access memory (DRAM) that continues to pose a significant threat to various systems. However, we find that conventional load-based attacks are becoming highly ineffective on the most…
Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-training methods. While longer reasoning traces can improve…
JEDEC has introduced the Per Row Activation Counting (PRAC) framework for DDR5 and future DRAMs to enable precise counting of DRAM row activations using per-row activation counts. While recent PRAC implementations enable holistic mitigation…
As DRAM and other transistor-based memory technologies approach their scalability limits, alternative storage solutions like Phase-Change Memory (PCM) are gaining attention for their scalability, fast access times, and zero leakage power.…
Deep learning-based recommendation models (DLRMs) are widely deployed in commercial applications to enhance user experience. However, the large and sparse embedding layers in these models impose substantial memory bandwidth bottlenecks due…
RowHammer attacks are a growing security and reliability concern for DRAMs and computer systems as they can induce many bit errors that overwhelm error detection and correction capabilities. System-level solutions are needed as process…
The emerging wide area monitoring systems (WAMS) have brought significant improvements in electric grids' situational awareness. However, the newly introduced system can potentially increase the risk of cyber-attacks, which may be disguised…
Modern business applications and scientific databases call for inherently dynamic data storage environments. Such environments are characterized by two challenging features: (a) they have little idle system time to devote on physical…
Machine learning models used in medical applications often face challenges due to the covariate shift, which occurs when there are discrepancies between the distributions of training and target data. This can lead to decreased predictive…
Indexes provide a method to access data in databases quickly. It can improve the response speed of subsequent queries by building a complete index in advance. However, it also leads to a huge overhead of the continuous updating during…
ZZ crosstalk and decoherence hinder superconducting quantum computing. To enhance parallelism in mitigating ZZ crosstalk, we formulate the problem by integrating quantum cycles and two forms of qubit interference. We then propose CYCO, a…
RowHammer is a circuit-level DRAM vulnerability, where repeatedly activating and precharging a DRAM row, and thus alternating the voltage of a row's wordline between low and high voltage levels, can cause bit flips in physically nearby…
The escalating frequency of cyber-attacks poses significant challenges for organisations, particularly small enterprises constrained by limited in-house expertise, insufficient knowledge, and financial resources. This research presents a…
Neural Machine Translation models are extremely data and compute-hungry. However, not all data points contribute equally to model training and generalization. Data pruning to remove the low-value data points has the benefit of drastically…
Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a…
Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data. Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the…
Neural language models deployed in real-world applications must continually adapt to new tasks and domains without forgetting previously acquired knowledge. This work presents a comparative empirical study of catastrophic forgetting…