Related papers: CHERI Performance Enhancement for a Bytecode Inter…
Mixture-of-Experts (MoE) architectures scale language models by activating only a subset of specialized expert networks for each input token, thereby reducing the number of floating-point operations. However, the growing size of modern MoE…
Advancements in large language models (LLMs) are showing promising impact in software development and programming assistance. However, these models struggle when operating on low-level backend code. This challenge is exacerbated in the…
The complexity and size increase of software has extended the delay for developers as they wait for code analysis and code merge. With the larger and more complex software, more developers nowadays are developing software with large source…
Speech signal analysis poses significant challenges, particularly in tasks such as speech quality evaluation and profiling, where the goal is to predict multiple perceptual and objective metrics. For instance, metrics like PESQ (Perceptual…
Improvements in the performance of computing systems, driven by Moore's Law, have transformed society. As such hardware-driven gains slow down, it becomes even more important for software developers to focus on performance and efficiency…
Parameter-efficient fine-tuning (PEFT) has become a practical route for adapting large language models to downstream tasks, with LoRA-style methods being particularly attractive because they are inexpensive to train and easy to deploy. Most…
Large Language Models (LLMs) have demonstrated significant capability in code generation, but their potential in code efficiency optimization remains underexplored. Previous LLM-based code efficiency optimization approaches exclusively…
Hardware heterogeneity is here to stay for high-performance computing. Large-scale systems are currently equipped with multiple GPU accelerators per compute node and are expected to incorporate more specialized hardware. This shift in the…
Mobile workloads incur heavy frontend stalls due to increasingly large code footprints as well as long repeat cycles. Existing instruction-prefetching techniques suffer from low coverage, poor timeliness, or high cost. We provide a SW/HW…
Embedded and IoT devices, largely powered by microcontroller units (MCUs), could be made more intelligent by leveraging on-device deep learning. One of the main challenges of neural network inference on an MCU is the extremely limited…
This paper reveals the phenomenon of parameter heterogeneity in large language models (LLMs). We find that a small subset of "cherry" parameters exhibit a disproportionately large influence on model performance, while the vast majority of…
Transformer architectures are increasingly effective at processing and generating very long chunks of texts, opening new perspectives for document-level machine translation (MT). In this work, we challenge the ability of MT systems to…
The continuing advancement of memory technology has not only fueled a surge in performance, but also substantially exacerbate reliability challenges. Traditional solutions have primarily focused on improving the efficiency of protection…
In this paper, we propose a sequential and incremental precoder design for downlink joint transmission (JT) network MIMO systems with imperfect backhaul links. The objective of our design is to minimize the maximum of the sub-stream mean…
Automatic Post-Editing (APE) systems often struggle with over-correction, where unnecessary modifications are made to a translation, diverging from the principle of minimal editing. In this paper, we propose a novel technique to mitigate…
Irregular memory access patterns pose performance and user productivity challenges on distributed-memory systems. They can lead to fine-grained remote communication and the data access patterns are often not known until runtime. The…
The rise of Artificial Intelligence (AI)-and particularly Large Language Models (LLMs) for code-has reshaped Software Engineering (SE) by enabling the automation of tasks such as code generation, bug detection, and repair. However, these…
We introduce SIRI, Scaling Iterative Reinforcement Learning with Interleaved Compression, a simple yet effective RL approach for Large Reasoning Models (LRMs) that enables more efficient and accurate reasoning. Existing studies have…
Large Language Models (LLMs) have demonstrated remarkable capabilities across various NLP tasks but struggle with code-mixed (or code-switched) language understanding. For example, prior work benchmarking the performance of multilingual…
The rapid advancement of Artificial Intelligence (AI) has created unprecedented demands for computational power, yet methods for evaluating the performance, efficiency, and environmental impact of deployed models remain fragmented. Current…