Related papers: An Operational Framework for Specifying Memory Mod…

As autonomous agents become increasingly sophisticated, validating their sequential behavior presents a significant challenge. Traditional testing approaches require manual specification, exact sequence matching, or thousands of training…

Expandable networks have demonstrated their advantages in dealing with catastrophic forgetting problem in incremental learning. Considering that different tasks may need different structures, recent methods design dynamic structures adapted…

Recent works on instruction tuning (IT) have achieved great performance with zero-shot generalizability to unseen tasks. With additional context (e.g., task definition, examples) provided to models for fine-tuning, they achieved much higher…

User simulation is important for developing and evaluating human-centered AI, yet current student simulation in educational applications has significant limitations. Existing approaches focus on single learning experiences and do not…

We propose an axiomatic generic framework for modelling weak memory. We show how to instantiate this framework for SC, TSO, C++ restricted to release-acquire atomics, and Power. For Power, we compare our model to a preceding operational…

An accurate prediction of scheduling and execution of instruction streams is a necessary prerequisite for predicting the in-core performance behavior of throughput-bound loop kernels on out-of-order processor architectures. Such predictions…

In recent years, we have witnessed an increased interest in temporal modeling of patient records from large scale Electronic Health Records (EHR). While simpler RNN models have been used for such problems, memory networks, which in other…

As deep learning models continue to increase in size, the memory requirements for training have surged. While high-level techniques like offloading, recomputation, and compression can alleviate memory pressure, they also introduce…

Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks and has become the state-of-the-art for visual object tracking. The model stores information from previous frames in a memory bank, enabling…

Dataflow languages provide natural support for specifying constraints between objects in dynamic applications, where programs need to react efficiently to changes of their environment. Researchers have long investigated how to take…

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

This paper describes an end-to-end (E2E) neural architecture for the audio rendering of small portions of display content on low resource personal computing devices. It is intended to address the problem of accessibility for vision-impaired…

Meta-learning of numerical algorithms for a given task consists of the data-driven identification and adaptation of an algorithmic structure and the associated hyperparameters. To limit the complexity of the meta-learning problem, neural…

Basic block reordering is an important step for profile-guided binary optimization. The state-of-the-art goal for basic block reordering is to maximize the number of fall-through branches. However, we demonstrate that such orderings may…

Continual learning requires models to adapt to new data while preserving previously acquired knowledge. At its core, this challenge can be viewed as principled one-step adaptation: incorporating new information with minimal interference to…

Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep…

Recently, instruction-based image editing (IIE) has received widespread attention. In practice, IIE often modifies only specific regions of an image, while the remaining areas largely remain unchanged. Although these two types of regions…

The recent Spectre attacks has demonstrated the fundamental insecurity of current computer microarchitecture. The attacks use features like pipelining, out-of-order and speculation to extract arbitrary information about the memory contents…

In this article, we introduce an instruction set architecture (ISA) for processing-in-memory (PIM) based deep neural network (DNN) accelerators. The proposed ISA is for DNN inference on PIM-based architectures. It is assumed that the…

We propose an efficient retraining strategy for a parameterized Reduced Order Model (ROM) that attains accuracy comparable to full retraining while requiring only a fraction of the computational time and relying solely on sparse…