Related papers: Louvre: Lightweight Ordering Using Versioning for …

Speculative techniques in microarchitectures relax various dependencies in programs, which contributes to the complexity of (weak) memory models. We show using WMM, a new weak memory model, that the model becomes simpler if it includes…

Concurrent systems are notoriously difficult to analyze, and technological advances such as weak memory architectures greatly compound this problem. This has renewed interest in partial order semantics as a theoretical foundation for formal…

L1 instruction (L1-I) cache misses are a source of performance bottleneck. Sequential prefetchers are simple solutions to mitigate this problem; however, prior work has shown that these prefetchers leave considerable potentials uncovered.…

In the shared variable model of concurrency, guarded atomic actions restrict the possible interference between processes by regions of atomic execution. The guard specifies the condition for entering an atomic region. That is a convenient…

Out-of-order speculation, a technique ubiquitous since the early 1990s, remains a fundamental security flaw. Via attacks such as Spectre and Meltdown, an attacker can trick a victim, in an otherwise entirely correct program, into leaking…

Collaborative inference has received significant research interest in machine learning as a vehicle for distributing computation load, reducing latency, as well as addressing privacy preservation in communications. Recent collaborative…

We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs. LLM-generated proofs are notoriously correct-but-verbose and brittle across…

As state of the art neural networks (NNs) continue to grow in size, their resource-efficient implementation becomes ever more important. In this paper, we introduce a compression scheme that reduces the number of computations required for…

We propose to accelerate the rate of convergence of the pattern recognition task by directly minimizing the variance diameters of certain hypothesis spaces, which are critical quantities in fast-convergence results.We show that the variance…

Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit endlessly many surface forms, making jailbreak mitigation…

Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention for LLM post-training, yet training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training…

In the wake of the explosive growth in smartphones and cyberphysical systems, there has been an accelerating shift in how data is generated away from centralised data towards on-device generated data. In response, machine learning…

Modern processors deploy a variety of weak memory models, which for efficiency reasons may execute instructions in an order different to that specified by the program text. The consequences of instruction reordering can be complex and…

This paper presents the interesting observation that by performing fewer of the optimizations available in a standard compiler optimization level such as -O2, while preserving their original ordering, significant savings can be achieved in…

Message passing programs commonly use buffers to avoid unnecessary synchronizations and to improve performance by overlapping communication with computation. Unfortunately, using buffers makes the program no longer portable, potentially…

We study the design of storage-efficient algorithms for emulating atomic shared memory over an asynchronous, distributed message-passing system. Our first algorithm is an atomic single-writer multi-reader algorithm based on a novel…

Deep Neural Networks are increasingly leveraging sparsity to reduce the scaling up of model parameter size. However, reducing wall-clock time through sparsity and pruning remains challenging due to irregular memory access patterns, leading…

We model the cadence of AI product releases, i.e. quiet spells, reversible patches, and rarer pivots, as optimal exercise of strategic real options under reputational learning. A privately observed technical state follows a diffusion. The…

Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (RLVR) pipelines filter out ``easy'' problems for training…

Machine learning is increasingly permeating radio-based localization services. To keep results credible and comparable, everyday workflows should make rigorous experiment specification and exact repeatability the default, without blocking…