Related papers: PlanCompiler: A Deterministic Compilation Architec…

Smart-contract exploits have caused billions of USD in cumulative losses, yet audits remain expensive and slow. Automated tools have emerged to close this gap, but each class has a characteristic failure mode. Static analyzers report…

Reasoning LLMs (RLMs) such as OpenAI o1, DeepSeek-R1, and Qwen3 deliver strong multi-step reasoning through chain-of-thought generation, but their large model sizes and lengthy decode-time outputs make them costly to deploy and unsuitable…

Large language model (LLM) merging has become a key technique in modern LLM development pipelines, enabling the integration of multiple task- or domain-specific expert models without retraining. However, as the number of experts grows,…

Automated data preparation is crucial for democratizing machine learning, yet existing reinforcement learning (RL) based approaches suffer from inefficient exploration in the vast space of possible preprocessing pipelines. We present…

Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory architecture comprising six cognitive mechanisms: (1) sleep-phase consolidation, (2)…

Large language models (LLMs) have become increasingly prominent in academia and industry due to their remarkable performance in diverse applications. As these models evolve with increasing parameters, they excel in tasks like sentiment…

A compiler processes the code written in a high level language and produces machine executable code. The compiler writers often face the challenge of keeping the compilation times reasonable. That is because aggressive optimization passes…

Linear Programming (LP) is widely applied in industry and is a key component of various other mathematical problem-solving techniques. Recent work introduced an LP compiler translating polynomial-time, polynomial-space algorithms into…

We introduce DafnyCOMP, a benchmark for evaluating large language models (LLMs) on compositional specification generation in Dafny. Unlike prior benchmarks that focus on single-function tasks, DafnyCOMP targets programs composed of multiple…

Fast compilation is important when compilation occurs at runtime, such as query compilers in modern database systems and WebAssembly virtual machines in modern browsers. We present copy-and-patch, an extremely fast compilation technique…

The rapidly evolving landscape of AI and machine learning workloads has widened the gap between high-level domain operations and efficient hardware utilization. Achieving near-peak performance still demands deep hardware expertise-experts…

Decompilation is widely used in reverse engineering to recover high-level language code from binary executables. While recent approaches leveraging Large Language Models (LLMs) have shown promising progress, they typically treat assembly…

Core systems like key-value stores have historically taken years to build, and are designed to be general so as to amortize cost across deployments, paying a significant performance cost. We argue that LLM-based coding agents now make a…

Checklists have emerged as a popular approach for interpretable and fine-grained evaluation, particularly with LLM-as-a-Judge. Beyond evaluation, these structured criteria can serve as signals for model alignment, reinforcement learning,…

Conditional graphic layout generation, which automatically maps user constraints to high-quality layouts, has attracted widespread attention today. Although recent works have achieved promising performance, the lack of versatility and data…

Accurate and fast performance prediction for dataflow-based accelerators is vital for efficient hardware design and design space exploration, yet existing methods struggle to generalize across architectures, applications, and…

Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. We collect pairs of naturalistic and synthetic reasoning tasks to…

Compilers are essential for the performance and correct execution of software and hold universal relevance across various scientific disciplines. Despite this, there is a notable lack of tools for testing and evaluating them, especially…

LLM-guided compiler optimization has recently shown promise, but existing approaches rely on a single large LLM throughout search, making them expensive and excluding smaller models. We pose the research question: whether heterogeneous LLMs…

Deep generative models for tabular data (GANs, diffusion models, and LLM-based generators) exhibit highly non-uniform behavior across datasets; the best-performing synthesizer family depends strongly on distributional stressors such as…