Related papers: Eliminate Branches by Melding IR Instructions

LFENCE/JMP is an existing software mitigation option for Branch Target Injection (BTI) and similar transient execution attacks stemming from indirect branch predictions, which is commonly used on AMD processors. However, the effectiveness…

Linear programming (LP) is an extremely useful tool and has been successfully applied to solve various problems in a wide range of areas, including operations research, engineering, economics, or even more abstract mathematical areas such…

Complex multi-step reasoning tasks, such as solving mathematical problems or generating code, remain a significant hurdle for even the most advanced large language models (LLMs). Verifying LLM outputs with an Outcome Reward Model (ORM) is a…

Neural networks are known to be vulnerable to adversarial attacks, which are small, imperceptible perturbations that can significantly alter the network's output. Conversely, there may exist large, meaningful perturbations that do not…

Edit distances between merge trees of scalar fields have many applications in scientific visualization, such as ensemble analysis, feature tracking or symmetry detection. In this paper, we propose branch mappings, a novel approach to the…

Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier-guided adaptive framework treating reasoning as iterative…

To take full advantage of a specific hardware target, performance engineers need to gain control on compilers in order to leverage their domain knowledge about the program and hardware. Yet, modern compilers are poorly controlled, usually…

Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce…

Efficiency in instruction fetching is critical to performance, and this requires the primary structures--L1 instruction caches (L1i), branch target buffers (BTB) and instruction TLBs (iTLB)--to have the requisite information when needed.…

This report presents some early results on code generation targeting tensor cores on NVIDIA GPUs using the MLIR compiler infrastructure. The state-of-the-art in high-performance deep learning today is primarily driven by manually optimized…

The massive scale of modern AI accelerators presents critical challenges to traditional fault assessment methodologies, which face prohibitive computational costs and provide poor coverage of critical failure modes. This paper introduces…

Segmenting small and sparse structures in large-scale images is fundamentally constrained by voxel-level, lattice-bound computation and extreme class imbalance -- dense, full-resolution inference scales poorly and forces most pipelines to…

Implicit Neural Representations (INRs) parameterize continuous signals via multilayer perceptrons (MLPs), enabling compact, resolution-independent modeling for tasks like image, audio, and 3D reconstruction. However, fitting high-resolution…

Large Language Models (LLMs) have transformed task automation and content generation across various domains while incorporating safety filters to prevent misuse. We introduce a novel jailbreaking framework that employs distributed prompt…

Model merging has emerged as a promising approach for unifying independently fine-tuned models into an integrated framework, significantly enhancing computational efficiency in multi-task learning. Recently, several SVD-based techniques…

In this work, we propose EarlyMalDetect, a novel approach for early Windows malware detection based on sequences of API calls. Our approach leverages generative transformer models and attention-guided deep recurrent neural networks to…

In addition to signature-based and heuristics-based detection techniques, machine learning (ML) is widely used to generalize to new, never-before-seen malicious software (malware). However, it has been demonstrated that ML models can be…

Python's dynamic nature complicates testing and increases the possibility that some defects evade detection, so an effective fault prediction becomes essential. We examine whether post-release faults can be predicted using modern ML and DL.…

Prompt engineering is very important to enhance the performance of large language models (LLMs). When dealing with complex issues, prompt engineers tend to distill multiple patterns from examples and inject relevant solutions to optimize…

In the past years, software reverse engineering dealt with source code understanding. Nowadays, it is levered to software requirements abstract level, supported by feature model notations, language independent, and simpler than the source…