Related papers: Elzar: Triple Modular Redundancy using Intel Advan…

Recent advances in Entity Resolution (ER) have leveraged Large Language Models (LLMs), achieving strong performance but at the cost of substantial computational resources or high financial overhead. Existing LLM-based ER approaches operate…

Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i.e., samples). For this purpose,…

Multi-threaded programs have many applications which are widely used such as operating systems. Analyzing multi-threaded programs differs from sequential ones; the main feature is that many threads execute at the same time. The effect of…

Current radio frequency (RF) sensors at the Edge lack the computational resources to support practical, in-situ training for intelligent spectrum monitoring, and sensor data classification in general. We propose a solution via Deep Delay…

Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resort to explicit vectorization using intrinsics, as…

Triple Modular Redundancy (TMR) has been traditionally used to ensure complete tolerance to a single fault or a faulty processing unit, where the processing unit may be a circuit or a system. However, TMR incurs more than 200% overhead in…

In the past decade, Deep Learning (DL) systems have been widely deployed in various domains to facilitate our daily life. Meanwhile, it is extremely challenging to ensure the correctness of DL systems (e.g., due to their intrinsic…

Large-scale Vision-Language-Action (VLA) models offer semantic generalization but suffer from high inference latency, limiting them to low-frequency batch-and-execute paradigm. This frequency mismatch creates an execution blind spot,…

Existing iterative compilation and machine-learning-based optimization techniques have been proven very successful in achieving better optimizations than the standard optimization levels of a compiler. However, they were not engineered to…

Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and…

With recent algorithmic improvements and easy-to-use libraries, equality saturation is being picked up for hardware design, program synthesis, theorem proving, program optimization, and more. Existing work on using equality saturation for…

We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when given malign instructions, our method specifically trains the model to change how it…

Class Incremental Learning (CIL) is challenging due to catastrophic forgetting. On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data. Recent exemplar-free CIL…

Composed Image Retrieval (CIR) aims to retrieve target images based on a hybrid query comprising a reference image and a modification text. Early dual-tower Vision-Language Models (VLMs) struggle with cross-modality compositional reasoning…

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However,…

Multi-core machines are ubiquitous. However, most inductive logic programming (ILP) approaches use only a single core, which severely limits their scalability. To address this limitation, we introduce parallel techniques based on…

Hybrid cloud-edge infrastructures now support latency-critical workloads ranging from autonomous vehicles and surgical robotics to immersive AR/VR. However, they continue to experience crippling long-tail latency spikes whenever bursty…

In recent years, large language models have achieved great success due to their unprecedented size. However, training these models poses a challenge for most researchers as it requires a substantial number of GPUs. To reduce GPU memory…

Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches have been proposed…

The growing adoption of Large Language Models (LLMs) across various domains has driven the demand for efficient and scalable AI-serving solutions. Deploying LLMs requires optimizations to manage their significant computational and data…