Related papers: Making Strong Error-Correcting Codes Work Effectiv…

Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks by generating long, multi-step reasoning trajectories, but inference-time scaling incurs substantial deployment cost. A key challenge is that generation…

Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a percentage point. At the same time, the computational cost of evaluating modern LLMs has…

The massive scale of modern AI accelerators presents critical challenges to traditional fault assessment methodologies, which face prohibitive computational costs and provide poor coverage of critical failure modes. This paper introduces…

This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation…

Driven by recent advances in artificial intelligence (AI), a growing literature has demonstrated the potential for using large language models (LLMs) as scalable surrogates to generate human-like responses in many business applications. Two…

Hardware and software of secured embedded systems are prone to physical attacks. In particular, fault injection attacks revealed vulnerabilities on the data and the control flow allowing an attacker to break cryptographic or secured…

Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on the same GPU cluster, forcing the system to switch between inference and training workloads. This serial context…

Multiple-input multiple-output (MIMO) technology has been regarded as one of the most important technologies to enable emerging applications in current and next generation wireless communication systems, for which signal detection methods…

Branch and bound algorithms have been developed for reliability analysis of coherent systems. They exhibit a set of advantages; in particular, they can find a computationally efficient representation of a system failure or survival event,…

Hybrid-reasoning large language models (LLMs) expose explicit controls over reasoning effort, allowing users or systems to trade off answer quality against inference cost. However, existing methods for adaptive thinking-mode selection are…

Large reasoning models (LRMs) achieve strong accuracy through test-time scaling, generating longer chains of thought or sampling multiple solutions, but at steep costs in tokens and latency. We argue that memory is a core ingredient for…

When a system's constraints change abruptly, the system's reachability safety does no longer sustain. Thus, the system can reach a forbidden/dangerous value. Conventional remedy practically involves online controller redesign (OCR) to…

Addressing class imbalance is a central challenge in credit card fraud detection, as it directly impacts predictive reliability in real-world financial systems. To overcome this, the study proposes an enhanced workflow based on the…

Large language models (LLMs) empowered by chain-of-thought reasoning have achieved impressive accuracy on complex tasks but suffer from excessive inference costs and latency when applied uniformly to all problems. We propose SABER…

In most error correction coding (ECC) frameworks, the typical error metric is the bit error rate (BER) which measures the number of bit errors. For this metric, the positions of the bits are not relevant to the decoding, and in many noise…

Channel coding is vital for reliable sixth-generation (6G) data transmission, employing diverse error correction codes for various application scenarios. Traditional decoders require dedicated hardware for each code, leading to high…

Deep Neural Networks (DNNs) continue to grow in complexity with Large Language Models (LLMs) incorporating vast numbers of parameters. Handling these parameters efficiently in traditional accelerators is limited by data-transmission…

Processing-in-memory (PIM) based on emerging devices such as memristors is more vulnerable to noise than traditional memories, due to the physical non-idealities and complex operations in analog domains. To ensure high reliability,…

LLM cascades and model routing promise lower inference cost by sending easy queries to a small model and escalating hard ones to a large model, but most deployed routers use uncalibrated confidence scores and require per-workload threshold…

Community GPU platforms are emerging as a cost-effective and democratized alternative to centralized GPU clusters for AI workloads, aggregating idle consumer GPUs from globally distributed and heterogeneous environments. However, their…