{"total":48,"rows":[{"id":"2507.11948","title":"Kevin: Multi-Turn RL for Generating CUDA Kernels","created":"2025-07-16","cited_by_count":78,"area":null},{"id":"2507.05687","title":"AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs","created":"2025-07-08","cited_by_count":40,"area":null},{"id":"2507.23194","title":"Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks","created":"2025-07-31","cited_by_count":32,"area":null},{"id":"2601.00227","title":"FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems","created":"2026-01-01","cited_by_count":25,"area":null},{"id":"2603.12440","title":"KernelFoundry: Hardware-aware evolutionary GPU kernel optimization","created":"2026-03-12","cited_by_count":13,"area":null},{"id":"2605.04956","title":"KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels","created":"2026-05-06","cited_by_count":12,"area":null},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2603.02236","title":"CUDABench: Benchmarking LLMs for Text-to-CUDA Generation","created":"2026-02-13","cited_by_count":10,"area":null},{"id":"2603.07169","title":"Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2512.22147","title":"GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs","created":"2025-12-15","cited_by_count":3,"area":null},{"id":"2601.12698","title":"A Two-Stage GPU Kernel Tuner Combining Semantic Refactoring and Search-Based Optimization","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2602.11715","title":"DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2602.12305","title":"OptiML: An End-to-End Framework for Program Synthesis and CUDA Kernel Optimization","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2603.10846","title":"Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2603.23566","title":"AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2604.16625","title":"AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2606.16497","title":"daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2607.14541","title":"Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent","created":"2026-07-16","cited_by_count":3,"area":null},{"id":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2605.05023","title":"CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels","created":"2026-05-06","cited_by_count":2,"area":null},{"id":"2605.26118","title":"Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU","created":"2026-04-16","cited_by_count":2,"area":null},{"id":"2607.20466","title":"JAXBench: Benchmarking Autonomous TPU Kernel Optimization","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2608.12004","title":"RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2509.14265","title":"Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2512.20861","title":"Memory-Efficient Acceleration of Block Low-Rank Foundation Models on Resource Constrained GPUs","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2603.11935","title":"MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.08467","title":"CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.09708","title":"Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2607.20518","title":"CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.25061","title":"DataKernelBench: Can LLMs Optimize Database Queries on GPUs?","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.10226","title":"$\\Phi$-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2511.19438","title":"Opt4GPTQ: Co-Optimizing Memory and Computation for 4-bit GPTQ Quantized LLM Inference on Heterogeneous Platforms","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2601.02045","title":"The New Compiler Stack: A Survey on the Synergy of LLMs and Compilers","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2605.08455","title":"CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.17978","title":"AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.04023","title":"CodegenBench: Can LLMs Write Efficient Code Across Architectures?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.23089","title":"Compiler-Grounded Hierarchical Diagnosis for LLM-Based Triton Kernel Optimization","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2608.12700","title":"A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the Gated-Linear-Recurrence Family","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.17379","title":"PTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization with Architecture-specific PTX","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.20711","title":"AsmEvo: Agentic Assembly-Level Optimization of AMD GPU Kernels with Functional Equivalence Verification","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.22220","title":"Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.29626","title":"iCoder-27B: Recursive AI-Led Development of Frontier Industrial Coding Model","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.33074","title":"KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35639","title":"GPUPhysBench: Benchmarking Coding Agents for Correct and Efficient GPU Physics Simulation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36800","title":"AI as a Compiler: Compiling Triton kernels without the Triton compiler","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.05014","title":"MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05683","title":"RESOLVE: Language-Agnostic Validation of GPU Kernels Through Testing, Reduction, and Proof","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.17321","title":"GPU Goldmines: Tunable WebGPU Kernels for Edge LLM Inference","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}