{"total":25,"rows":[{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88,"area":null},{"id":"2506.20807","title":"GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization","created":"2025-06-25","cited_by_count":22,"area":null},{"id":"2603.28458","title":"HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention","created":"2026-03-30","cited_by_count":12,"area":null},{"id":"2508.02215","title":"LeanK: Learnable K Cache Channel Pruning for Efficient Decoding","created":"2025-08-04","cited_by_count":7,"area":null},{"id":"2510.14719","title":"Tawa: Automatic Warp Specialization for Modern GPUs with Asynchronous References","created":"2025-10-16","cited_by_count":6,"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":"2608.12629","title":"CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution","created":"2026-08-12","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":"2602.04361","title":"SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2605.04569","title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2511.23319","title":"Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2601.19092","title":"Axe: A Simple Unified Layout Abstraction for Machine Learning Compilers","created":"2026-01-27","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":"2606.27153","title":"DMuon: Efficient Distributed Muon Training with Near-Adam Overhead","created":"2026-06-25","cited_by_count":3,"area":null},{"id":"2605.29734","title":"HTAM: Hierarchical Transition-Attended Memory for Operator Optimization","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2511.08083","title":"HipKittens: Fast and Furious AMD Kernels","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2605.02568","title":"StreamIndex: Memory-Bounded Compressed Sparse Attention via Streaming Top-k","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.26344","title":"Axon: A Synthesizing Superoptimizer for Tensor Programs","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.02584","title":"RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.18357","title":"Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.04956","title":"ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing","created":"2026-08-05","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":"2609.36800","title":"AI as a Compiler: Compiling Triton kernels without the Triton compiler","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38166","title":"LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.07742","title":"Cleave: Scaling Tensor Program Optimization via Decoupled Algebraic Search and Operator Scheduling","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}