Related papers: ERASER: Efficient RTL FAult Simulation Framework w…

Fault-tolerance is critically important in highly-distributed modern cloud applications. Solutions such as Temporal, Azure Durable Functions, and Beldi hide fault-tolerance complexity from developers by persisting execution state and…

Computer simulations have become essential for analyzing complex systems, but high-fidelity simulations often come with significant computational costs. To tackle this challenge, multi-fidelity computer experiments have emerged as a…

Machine Learning (ML) models are susceptible to evasion attacks. Evasion accuracy is typically assessed using aggregate evasion rate, and it is an open question whether aggregate evasion rate enables feature-level diagnosis on the effect of…

Deep learning (DL) compilers rely on cost models and auto-tuning to optimize tensor programs for target hardware. However, existing approaches depend on large offline datasets, incurring high collection costs and offering suboptimal…

Error mitigation is essential for unlocking the full potential of quantum algorithms and accelerating the timeline toward quantum advantage. As quantum hardware progresses to push the boundaries of classical simulation, efficient and robust…

Leaking information about the execution behavior of critical real-time tasks may lead to serious consequences, including violations of temporal constraints and even severe failures. We study information leakage for a special class of…

Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on inference latency. This bottleneck has emerged as a central obstacle…

Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often…

Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging. This paper presents novel techniques that leverage the temporal…

Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention for LLM post-training, yet training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training…

Traditional error detection approaches require user-defined parameters and rules. Thus, the user has to know both the error detection system and the data. However, we can also formulate error detection as a semi-supervised classification…

Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative…

This paper provides a link and system level study of the downlink using OFDMA techniques based on LTE systems. At the link level, the Block Error Rate (BLER) performance curves are generated and 10 % points of BLER curves, calculated under…

Ensuring the safety and efficiency of AI systems is a central goal of modern research. Formal verification provides guarantees of neural network robustness, while early exits improve inference efficiency by enabling intermediate…

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…

Extract, Transform, Load (ETL) is an integral part of Data Warehousing (DW) implementation. The commercial tools that are used for this purpose captures lot of execution trace in form of various log files with plethora of information.…

Environmental noise (e.g.heat, ionized particles, etc.) causes transient faults in hardware, which lead to corruption of stored values. Mission-critical devices require such faults to be mitigated by fault-tolerance --- a combination of…

Learning effective netlist representations is fundamentally constrained by the scarcity of labeled datasets, as real designs are protected by Intellectual Property (IP) and costly to annotate. Existing work therefore focuses on small-scale…

Robust Recurrent Neural Networks (R-RENs) are a class of neural networks that have built-in system-theoretic robustness and incremental stability properties. In this manuscript, we leverage these properties to construct a data-driven Fault…

The paper algorithmizes the problem of regime change point identification for data measured in a system exhibiting impulsive behaviors. This is a fundamental challenge for annotation of measurement data relevant, e.g., for designing…