Related papers: ARGUS: Agentic GPU Optimization Guided by Data-Flo…

Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution. However, the effective adjustment of agentic workflows during execution has not been well studied. An…

3D Gaussian splatting (3DGS) is a transformative technique with profound implications on novel view synthesis and real-time rendering. Given its importance, there have been many attempts to improve its performance. However, with the…

Generating performant executables from high level languages is critical to software performance across a wide range of domains. Modern compilers perform this task by passing code through a series of well-studied optimizations at…

GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive…

Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…

Agentic Workflows (AWs) have emerged as a promising paradigm for solving complex tasks. However, the scalability of automating their generation is severely constrained by the high cost and latency of execution-based evaluation. Existing AW…

Real-world multimodal applications often require any-to-any capabilities, enabling both understanding and generation across modalities including text, image, audio, and video. However, integrating the strengths of autoregressive language…

Optimizing LLM-based agentic workflows is challenging for scaling AI capabilities. Current methods rely on coarse, end-to-end evaluation signals and lack fine-grained signals on where to refine, often resulting in inefficient or low-impact…

Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of the art systems scale inference time compute via parallel…

Agentic LLM applications increasingly execute user requests as multi-step workflows involving planning, tool use, branching, refinement, and synthesis. In such settings, users experience the end-to-end latency of an entire workflow, not the…

Serving Large Language Models (LLMs) is critical for AI-powered applications, yet it demands substantial computational resources, particularly in memory bandwidth and computational throughput. Low-precision computation has emerged as a key…

GPUs are critical for compute-intensive applications, yet emerging workloads such as recommender systems, graph analytics, and data analytics often exceed GPU memory capacity. Existing solutions allow GPUs to use CPU DRAM or SSDs as…

Predictive atomistic simulations have propelled materials discovery, yet routine setup and debugging still demand computer specialists. This know-how gap limits Integrated Computational Materials Engineering (ICME), where state-of-the-art…

Large language models (LLMs) have shown impressive performance in general programming tasks. However, in Machine Learning Engineering (MLE) scenarios such as AutoML and Kaggle competitions, achieving high performance depends heavily on…

Analog/mixed-signal circuits are key for interfacing electronics with the physical world. Their design, however, remains a largely handcrafted process, resulting in long and error-prone design cycles. While the recent rise of AI-based…

Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a memory at inference time have been proposed, existing…

The surge in scientific publications challenges traditional review methods, demanding tools that integrate structured metadata with full-text analysis. Hybrid Retrieval Augmented Generation (RAG) systems, combining graph queries with vector…

FPGAs offer high performance, low latency, and energy efficiency for accelerated computing, yet adoption in scientific and edge settings is limited by the specialized hardware expertise required. High-level synthesis (HLS) boosts…

Deep learning compilers and vendor libraries deliver strong baseline performance but their performance is bounded by finite, engineer-curated catalogs. When these omit needed optimizations, practitioners substitute hand-written CUDA or…

Large Language Models (LLMs) show promise for automated code optimization but struggle without performance context. This work introduces Opal, a modular framework that connects performance analytics insights with the vast body of published…