Related papers: MicroGrad: A Centralized Framework for Workload Cl…
We propose MCGrad, a novel and scalable multicalibration algorithm. Multicalibration - calibration in subgroups of the data - is an important property for the performance of machine learning-based systems. Existing multicalibration methods…
One significant advantage of superconducting processors is their extensive design flexibility, which encompasses various types of qubits and interactions. Given the large number of tunable parameters of a processor, the ability to perform…
Reliability, security and stability of cloud services without sacrificing too much resources have become a desired feature in the area of workload management in clouds. The paper proposes and evaluates a lightweight framework for scheduling…
Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection layer when performing speculative decoding. Current methods for vocabulary pruning depend…
Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…
The ever-increasing complexity and operational diversity of modern Neural Networks (NNs) have caused the need for low-power and, at the same time, high-performance edge devices for AI applications. Coarse Grained Reconfigurable…
High-Performance Computing (HPC) centers and cloud providers support an increasingly diverse set of applications on heterogenous hardware. As Artificial Intelligence (AI) and Machine Learning (ML) workloads have become an increasingly…
Code clone detection (CCD) supports software maintenance, refactoring, and security analysis. Although pre-trained models capture code semantics, most work reduces CCD to binary classification, overlooking the heterogeneity of clone types…
While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, they often produce solutions that lack guarantees of correctness, robustness, and efficiency. This limitation is particularly acute in domains…
The increasing number of edge devices with enhanced sensing capabilities, such as smartphones, wearables, and IoT devices equipped with sensors, holds the potential for innovative smart-edge applications in healthcare. These devices…
Estimating instruction-level throughput is critical for many applications: multimedia, low-latency networking, medical, automotive, avionic, and industrial control systems all rely on tightly calculable and accurate timing bounds of their…
Mixture-of-Experts (MoE) has emerged as a promising approach to scale up deep learning models due to its significant reduction in computational resources. However, the dynamic nature of MoE leads to load imbalance among experts, severely…
We introduce a novel validation framework to measure the true robustness of learning models for real-world applications by creating source-inclusive and source-exclusive partitions in a dataset via clustering. We develop a robustness metric…
Coarse-grain reconfigurable architectures (CGRAs) are gaining traction thanks to their performance and power efficiency. Utilizing CGRAs to accelerate the execution of tight loops holds great potential for achieving significant overall…
A code clone is a pair of code fragments, within or between software systems that are similar. Since code clones often negatively impact the maintainability of a software system, several code clone detection techniques and tools have been…
At the intersection between traditional CPU architectures and more specialized options such as FPGAs or ASICs lies the family of reconfigurable hardware architectures, termed Coarse-Grained Reconfigurable Arrays (CGRAs). CGRAs are composed…
AI is undergoing a paradigm shift, with breakthroughs achieved by systems orchestrating multiple large language models (LLMs) and other complex components. As a result, developing principled and automated optimization methods for compound…
A reliable fault diagnosis system should not only accurately classify known health states but also effectively identify unknown faults. In multimode processes, samples belonging to the same health state often show multiple cluster…
Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…
We introduce ProofGrid, a benchmark suite for evaluating LLM reasoning through machine-checkable proofs rather than final answers alone. ProofGrid contains 15 tasks spanning proof writing, proof checking, proof masking, and proof…