English
Related papers

Related papers: Kevin: Multi-Turn RL for Generating CUDA Kernels

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard paradigm for reasoning in Large Language Models. However, optimizing solely for final-answer correctness often drives models into aimless, verbose exploration,…

Computation and Language · Computer Science 2026-01-14 Jiangshan Duo , Hanyu Li , Hailin Zhang , Yudong Wang , Sujian Li , Liang Zhao

GPU code optimization is a key performance bottleneck for HPC workloads as well as large-model training and inference. Although compiler optimizations and hand-written kernels can partially alleviate this issue, achieving…

Computation and Language · Computer Science 2026-01-26 Qiuyi Qu , Yicheng Sui , Yufei Sun , Rui Chen , Xiaofei Zhang , Yuzhi Zhang , Haofeng Wang , Ge Lan

Neural kernels have drastically increased performance on diverse and nonstandard data modalities but require significantly more compute, which previously limited their application to smaller datasets. In this work, we address this by…

Machine Learning · Statistics 2023-03-10 Ben Adlam , Jaehoon Lee , Shreyas Padhy , Zachary Nado , Jasper Snoek

Deep neural networks have recently achieved state of the art performance thanks to new training algorithms for rapid parameter estimation and new regularization methods to reduce overfitting. However, in practice the network architecture…

Machine Learning · Computer Science 2016-03-04 Minyoung Kim , Luca Rigazio

Reinforcement learning (RL) has shown empirical success in various real world settings with complex models and large state-action spaces. The existing analytical results, however, typically focus on settings with a small number of…

Machine Learning · Computer Science 2024-03-15 Sattar Vakili , Julia Olkhovskaya

Deep reinforcement learning has been recognized as an efficient technique to design optimal strategies for different complex systems without prior knowledge of the control landscape. To achieve a fast and precise control for quantum…

Quantum Physics · Physics 2021-01-05 Hailan Ma , Daoyi Dong , Steven X. Ding , Chunlin Chen

Reinforcement Learning (RL) trains agents to learn optimal behavior by maximizing reward signals from experience datasets. However, RL training often faces memory limitations, leading to execution latencies and prolonged training times. To…

Reinforcement learning with verifiable rewards (RLVR) generates hundreds of thousands of tokens per training step, with rollout generation dominating the computational cost. The overall token budget can be controlled along two main…

Machine Learning · Computer Science 2026-05-12 Haoyu Hu , Xuandong Zhao , Xuhai "Orson'' Xu , Nori Jacoby

Writing high-performance GPU kernels is among the most labor-intensive tasks in machine learning systems engineering. We present AutoKernel, an open-source framework that applies an autonomous agent loop to GPU kernel optimization for…

Machine Learning · Computer Science 2026-03-24 Jaber Jaber , Osama Jaber

Reinforcement learning (RL) has emerged as a powerful tool for tackling control problems, but its practical application is often hindered by the complexity arising from intricate reward functions with multiple terms. The reward hypothesis…

Machine Learning · Computer Science 2025-02-11 Kilian Freitag , Kristian Ceder , Rita Laezza , Knut Åkesson , Morteza Haghir Chehreghani

The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward…

Machine Learning · Computer Science 2024-12-31 Sinan Ibrahim , Mostafa Mostafa , Ali Jnadi , Hadi Salloum , Pavel Osinenko

Reinforcement learning (RL) is a framework to optimize a control policy using rewards that are revealed by the system as a response to a control action. In its standard form, RL involves a single agent that uses its policy to accomplish a…

Systems and Control · Electrical Eng. & Systems 2021-11-24 Juan Cervino , Juan Andres Bazerque , Miguel Calvo-Fullana , Alejandro Ribeiro

Optimizing GPU kernels presents a significantly greater challenge for large language models (LLMs) than standard code generation tasks, as it requires understanding hardware architecture, parallel optimization strategies, and performance…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-16 Nina Wiedemann , Quentin Leboutet , Michael Paulitsch , Diana Wofk , Benjamin Ummenhofer

Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…

Computer Vision and Pattern Recognition · Computer Science 2024-06-25 Owen Oertell , Jonathan D. Chang , Yiyi Zhang , Kianté Brantley , Wen Sun

Reinforcement Learning (RL) problems are being considered under increasingly more complex structures. While tabular and linear models have been thoroughly explored, the analytical study of RL under nonlinear function approximation,…

Machine Learning · Computer Science 2025-09-12 Aya Kayal , Sattar Vakili , Laura Toni , Alberto Bernacchia

Retrieval-augmented generation (RAG) systems rely on retrieval models for identifying relevant contexts and answer generation models for utilizing those contexts. However, retrievers exhibit imperfect recall and precision, limiting…

Computation and Language · Computer Science 2026-04-29 Jerry Huang , Siddarth Madala , Risham Sidhu , Cheng Niu , Hao Peng , Julia Hockenmaier , Tong Zhang

Large Language Models (LLMs) have demonstrated strong capabilities in general-purpose code generation. However, generating the code which is deeply hardware-specific, architecture-aware, and performance-critical, especially for massively…

Machine Learning · Computer Science 2025-06-12 Wentao Chen , Jiace Zhu , Qi Fan , Yehan Ma , An Zou

Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems. This work motivates the use of potential-based reward shaping to reduce…

Machine Learning · Computer Science 2023-12-19 Lauren H. Cooke , Harvey Klyne , Edwin Zhang , Cassidy Laidlaw , Milind Tambe , Finale Doshi-Velez

This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed to perform scalable reinforcement learning (RL) with large sequence models (such as transformers). With such models, existing systems such as Reverb…

Machine Learning · Computer Science 2023-10-10 Hanjing Wang , Man-Kit Sit , Congjie He , Ying Wen , Weinan Zhang , Jun Wang , Yaodong Yang , Luo Mai

In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external…

Computation and Language · Computer Science 2025-06-02 Fei Bai , Yingqian Min , Beichen Zhang , Zhipeng Chen , Wayne Xin Zhao , Lei Fang , Zheng Liu , Zhongyuan Wang , Ji-Rong Wen