{"total":18,"rows":[{"id":"2502.10517","title":"KernelBench: Can LLMs Write Efficient GPU Kernels?","created":"2025-02-14","cited_by_count":225,"area":null},{"id":"2512.22219","title":"MPK: A Compiler and Runtime for Mega-Kernelizing Tensor Programs","created":"2025-12-22","cited_by_count":15,"area":null},{"id":"2503.14376","title":"Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels","created":"2025-03-18","cited_by_count":13,"area":null},{"id":"2512.18134","title":"Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs","created":"2025-12-19","cited_by_count":5,"area":null},{"id":"2605.19269","title":"CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs","created":"2026-05-19","cited_by_count":5,"area":null},{"id":"2510.08726","title":"Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs","created":"2025-10-09","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":"2412.16481","title":"Flash3D: Super-scaling Point Transformers through Joint Hardware-Geometry Locality","created":"2024-12-21","cited_by_count":1,"area":null},{"id":"2511.08083","title":"HipKittens: Fast and Furious AMD Kernels","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2604.14825","title":"Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2511.12500","title":"Iris: First-Class Multi-GPU Programming Experience in Triton","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2603.06731","title":"PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2606.09682","title":"AutoMegaKernel: A Statically-Checked Agent Harness for Self-Retargeting Megakernel Synthesis","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.21157","title":"HIERA: Workload-Aware Planning Across Implementation Spaces for GPU Kernel Optimization","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.32882","title":"Improving Video Sparse Attention with Fine-grained Router and Sparse Rebasing","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.00053","title":"Format-Aware Fusion for Fast FP4 Pretraining","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.07098","title":"T-CCL: Resource Efficient and Performant Collective Communication using Tensor Memory Accelerator","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}