Related papers: Taming Weak Memory Models
The effective use of parallel computing resources to speed up algorithms in current multi-core parallel architectures remains a difficult challenge, with ease of programming playing a key role in the eventual success of various parallel…
Prompt-injected memory can improve reasoning without updating model weights, but it also creates a control problem: retrieved content helps only when it is applied in the right state. We study this problem in a strict training-free setting…
This work unifies insights from the systems and functional programming communities, in order to enable compositional reasoning about software which is nonetheless efficiently realizable in hardware. It exploits a correspondence between…
Developers of low-level systems code providing core functionality for operating systems and kernels must address hardware-level features of modern multicore architectures. A particular feature is pipelined "out-of-order execution" of the…
Transactional memory (TM) is an inherently optimistic abstraction: it allows concurrent processes to execute sequences of shared-data accesses (transactions) speculatively, with an option of aborting them in the future. Early TM designs…
The design of neural network architectures is frequently either based on human expertise using trial/error and empirical feedback or tackled via large scale reinforcement learning strategies performed over distinct discrete architecture…
Compute-in-memory (CIM) has emerged as a pivotal direction for accelerating workloads in the field of machine learning, such as Deep Neural Networks (DNNs). However, the effective exploitation of sparsity in CIM systems presents numerous…
Poor time predictability of multicore processors has been a long-standing challenge in the real-time systems community. In this paper, we make a case that a fundamental problem that prevents efficient and predictable real-time computing on…
Recent studies in interpretability have explored the inner workings of transformer models trained on tasks across various domains, often discovering that these networks naturally develop highly structured representations. When such…
We study weighted programming, a programming paradigm for specifying mathematical models. More specifically, the weighted programs we investigate are like usual imperative programs with two additional features: (1) nondeterministic…
The conventional von Neumann architecture has been revealed as a major performance and energy bottleneck for rising data-intensive applications. %, due to the intensive data movements. The decade-old idea of leveraging in-memory processing…
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…
As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training yields diminishing returns. While existing methods continue…
The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a…
State-space models (SSMs) have recently attention as an efficient alternative to computationally expensive attention-based models for sequence modeling. They rely on linear recurrences to integrate information over time, enabling fast…
Negative sampling approaches are prevalent in implicit collaborative filtering for obtaining negative labels from massive unlabeled data. As two major concerns in negative sampling, efficiency and effectiveness are still not fully achieved…
Existing methods for differentiable structure learning in discrete data typically assume that the data are generated from specific structural equation models. However, these assumptions may not align with the true data-generating process,…
Emerging computing architectures such as near-memory computing (NMC) promise improved performance for applications by reducing the data movement between CPU and memory. However, detecting such applications is not a trivial task. In this…
Auto-active program verification rests on the ability to effectively the translation from annotated programs into verification conditions that are then discharged by automated theorem provers in the background. Characteristic such tools,…
Much of what we remember is not due to intentional selection, but simply a by-product of perceiving. This raises a foundational question about the architecture of the mind: How does perception interface with and influence memory? Here,…