Related papers: A TRRIP Down Memory Lane: Temperature-Based Re-Ref…
Multicore systems present on-board memory hierarchies and communication networks that influence performance when executing shared memory parallel codes. Characterising this influence is complex, and understanding the effect of particular…
TurboGAP is a software package designed for efficient molecular dynamics simulations using Gaussian Approximation Potential (GAP) machine-learning interatomic potentials (MLIP). In this work, we enhance the capabilities of TurboGAP for…
Scaling Transformer-based click-through rate (CTR) models by stacking more parameters brings growing computational and storage overhead, creating a widening gap between scaling ambitions and the stringent industrial deployment constraints.…
Partitioning applications between NDP and host CPU cores causes inter-segment data movement overhead, which is caused by moving data generated from one segment (e.g., instructions, functions) and used in consecutive segments. Prior works…
Mobile computing is one of the main drivers of innovation, yet the future growth of mobile computing capabilities remains critically threatened by hardware constraints, such as the already extremely dense transistor packing and limited…
Video-text retrieval has witnessed remarkable progress driven by large-scale vision-language pretraining, yet most existing approaches inherit an implicit assumption from image-text retrieval: that visual semantics can be captured…
Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking. In LLM reasoning, existing works also explore various solutions for learning effective process…
The thermal unit commitment (UC) problem often can be formulated as a mixed integer quadratic programming (MIQP), which is difficult to solve efficiently, especially for large-scale instances. The tighter characteristic reduces the search…
Acoustic-sensor-based soft error resilience is particularly promising, since it can verify the absence of soft errors and eliminate silent data corruptions at a low hardware cost. However, the state-of-the-art work incurs a significant…
MPI collective operations provide a standardized interface for performing data movements within a group of processes. The efficiency of collective communication operations depends on the actual algorithm, its implementation, and the…
Tensor program tuning is a non-convex objective optimization problem, to which search-based approaches have proven to be effective. At the core of the search-based approaches lies the design of the cost model. Though deep learning-based…
To meet the practical requirements of low latency, low cost, and good privacy in online intelligent services, more and more deep learning models are offloaded from the cloud to mobile devices. To further deal with cross-device data…
Integrating time-frequency resource conversion (TFRC), a new network resource allocation strategy, with call admission control can not only increase the cell capacity but also reduce network congestion effectively. However, the optimal…
Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constrained environments. While modern frameworks incorporate various memory-saving techniques, they…
The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like quantization and distillation have further expanded PTM…
Lattice thermal conductivity (TC) of semiconductors is crucial for various applications, ranging from microelectronics to thermoelectrics. Data-driven approach can potentially establish the critical composition-property relationship needed…
Large-scale crop type classification is a task at the core of remote sensing efforts with applications of both economic and ecological importance. Current state-of-the-art deep learning methods are based on self-attention and use satellite…
To alleviate the performance and energy overheads of contemporary applications with large data footprints, we propose the Two Level Perceptron (TLP) predictor, a neural mechanism that effectively combines predicting whether an access will…
In recommendation systems, practitioners observed that increase in the number of embedding tables and their sizes often leads to significant improvement in model performances. Given this and the business importance of these models to major…
Retrieval-Augmented Generation (RAG) enhances coding tasks by incorporating retrieved code examples into prompts. However, lengthy prompts, often exceeding tens of thousands of tokens, introduce challenges related to limited context windows…