Related papers: Reference Capabilities for Flexible Memory Managem…
A circular program contains a data structure whose definition is self-referential or recursive. The use of such a definition allows efficient functional programs to be written and can avoid repeated evaluations and the creation of…
Emerging hybrid accelerator architectures for high performance computing are often suited for the use of a data-parallel programming model. Unfortunately, programmers of these architectures face a steep learning curve that frequently…
Recently, several Space-Time Memory based networks have shown that the object cues (e.g. video frames as well as the segmented object masks) from the past frames are useful for segmenting objects in the current frame. However, these methods…
In modern runtime systems, memory layout calculations are hand-coded in systems languages. Primitives in these languages are not powerful enough to describe a rich set of layouts, leading to reliance on ad-hoc macros, numerous interrelated…
Recent advances in optics have shown that solitons have a great potential for upgrading the future optical systems which demand fast and reliable data transfer. Along side Different architectures have evolved to realize an optical computer.…
We study abstraction for crash-resilient concurrent objects using non-volatile memory (NVM). We develop a library correctness criterion that is sound for ensuring contextual refinement in this setting, thus allowing clients to reason about…
A computer program is a set of electronic instructions executed from within the computer memory by the computer central processing unit. Its purpose is to control the functionalities of the computer allowing it to perform various tasks.…
We propose a novel deep visual odometry (VO) method that considers global information by selecting memory and refining poses. Existing learning-based methods take the VO task as a pure tracking problem via recovering camera poses from image…
Temporal context is essential for robotic manipulation because such tasks are inherently non-Markovian, yet mainstream VLA models typically overlook it and struggle with long-horizon, temporally dependent tasks. Cognitive science suggests…
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…
Over more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention. While recurrent models aim to compress the data into a fixed-size memory (called hidden state), attention…
Edge-computing requires high-performance energy-efficient embedded systems. Fixed-function or custom accelerators, such as FFT or FIR filter engines, are very efficient at implementing a particular functionality for a given set of…
Routing Problems are central to many real-world applications, yet remain challenging due to their (NP-)hard nature. Amongst existing approaches, heuristics often offer the best trade-off between quality and scalability, making them suitable…
Algorithms are ways of mapping problems to solutions. An algorithm is invertible precisely when this mapping is injective, such that the initial problem can be uniquely inferred from its solution. While invertible algorithms can be…
This paper describes our experiences creating Tornado: a practical and efficient heterogeneous programming framework for managed languages. The novel aspect of Tornado is that it turns the programming of heterogeneous systems from an…
Reference is a crucial property of language that allows us to connect linguistic expressions to the world. Modeling it requires handling both continuous and discrete aspects of meaning. Data-driven models excel at the former, but struggle…
Modern architectures provide weaker memory consistency guarantees than sequential consistency. These weaker guarantees allow programs to exhibit behaviours where the program statements appear to have executed out of program order.…
Inspired by how humans reason over discrete objects and their relationships, we explore whether compact object-centric and object-relation representations can form a foundation for multitask robotic manipulation. Most existing robotic…
Vision Transformers (ViT) serve as powerful vision models. Unlike convolutional neural networks, which dominated vision research in previous years, vision transformers enjoy the ability to capture long-range dependencies in the data.…
Aiming to augment generative models with external memory, we interpret the output of a memory module with stochastic addressing as a conditional mixture distribution, where a read operation corresponds to sampling a discrete memory address…