Related papers: Learning When to Optimize: Verified Optimization S…

With the rapid progress of deep learning and large language models (LLMs), companies now spend enormous sums executing GPU kernels. These kernels have, therefore, become prime targets for aggressive optimization. Recent efforts increasingly…

We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented post-training recipe. On the agent side, Kernel-Smith…

LLM-based coding agents rely on \emph{skills}, pre-packaged instruction sets that extend agent capabilities, yet every token of skill content injected into the context window incurs both monetary cost and attention dilution. To understand…

Reinforcement learning (RL) workloads take a notoriously long time to train due to the large number of samples collected at run-time from simulators. Unfortunately, cluster scale-up approaches remain expensive, and commonly used CPU…

Training deep neural networks is a highly nontrivial task, involving carefully selecting appropriate training algorithms, scheduling step sizes and tuning other hyperparameters. Trying different combinations can be quite labor-intensive and…

Despite many advances in knowledge engineering (KE), challenges remain in areas such as engineering knowledge graphs (KGs) at scale, keeping up with evolving domain knowledge, multilingualism, and multimodality. Recently, KE has used LLMs…

Large Language Models (LLMs) have shown notable potential in code generation for optimization algorithms, unlocking exciting new opportunities. This paper examines how LLMs, rather than creating algorithms from scratch, can improve existing…

Future computing systems, from handhelds to supercomputers, will undoubtedly be more parallel and heterogeneous than todays systems to provide more performance and energy efficiency. Thus, GPUs are increasingly being used to accelerate…

Formulating mathematical models from real-world decision problems is a core task in Operational Research, yet it typically requires considerable human expertise and effort, limiting practical application. Recent advances in large language…

Molecular design involves an enormous and irregular search space, where traditional optimizers such as Bayesian optimization, genetic algorithms, and generative models struggle to leverage expert knowledge or handle complex feedback.…

Training Large Language Models (LLMs) efficiently at scale presents a formidable challenge, driven by their ever-increasing computational demands and the need for enhanced performance. In this work, we introduce Liger-Kernel, an…

Recent breakthroughs in Large-scale language models (LLMs) have demonstrated impressive performance on various tasks. The immense sizes of LLMs have led to very high resource demand and cost for running the models. Though the models are…

Generative optimization uses large language models (LLMs) to iteratively improve artifacts (such as code, workflows or prompts) using execution feedback. It is a promising approach to building self-improving agents, yet in practice remains…

As the field of Large Language Models (LLMs) evolves at an accelerated pace, the critical need to assess and monitor their performance emerges. We introduce a benchmarking framework focused on knowledge graph engineering (KGE) accompanied…

Logic synthesis is a crucial phase in the circuit design process, responsible for transforming hardware description language (HDL) designs into optimized netlists. However, traditional logic synthesis methods are computationally intensive,…

With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the…

SIEM systems serve as a critical hub, employing rule-based logic to detect and respond to threats. Redundant or overlapping rules in SIEM systems lead to excessive false alerts, degrading analyst performance due to alert fatigue, and…

Maximizing performance on available GPU hardware is an ongoing challenge for modern AI inference systems. Traditional approaches include writing custom GPU kernels and using specialized model compilers to tune high-level code for specific…

Large language models (LLMs) are increasingly used to convert natural language descriptions into mathematical optimization formulations. Current evaluations often treat formulations as a whole, relying on coarse metrics like solution…

LLMs now form the backbone of AI agents across a diverse range of applications, including tool use, command-line interfaces, and web or computer interaction. These agentic LLM inference tasks are fundamentally different from chatbot-focused…