{"total":21,"rows":[{"id":"2502.03304","title":"Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning","created":"2025-02-05","cited_by_count":18,"area":null},{"id":"2404.04815","title":"Allo: A Programming Model for Composable Accelerator Design","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2410.22217","title":"Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective","created":"2024-10-29","cited_by_count":10,"area":null},{"id":"2504.16266","title":"TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs","created":"2025-04-22","cited_by_count":10,"area":null},{"id":"2407.17879","title":"HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline","created":"2024-07-25","cited_by_count":7,"area":null},{"id":"2502.16473","title":"TerEffic: Highly Efficient Ternary LLM Inference on FPGA","created":"2025-02-23","cited_by_count":6,"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":"2509.06794","title":"Dato: A Task-Based Programming Model for Dataflow Accelerators","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2411.03697","title":"TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2411.18148","title":"A Runtime-Adaptive Transformer Neural Network Accelerator on FPGAs","created":"2024-11-27","cited_by_count":3,"area":null},{"id":"2502.08807","title":"InTAR: Inter-Task Auto-Reconfigurable Accelerator Design for High Data Volume Variation in DNNs","created":"2025-02-12","cited_by_count":3,"area":null},{"id":"2509.00031","title":"End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2601.15710","title":"FlexLLM: Composable HLS Library for Flexible Hybrid LLM Accelerator Design","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2411.11852","title":"LUTMUL: Exceed Conventional FPGA Roofline Limit by LUT-based Efficient Multiplication for Neural Network Inference","created":"2024-11-01","cited_by_count":2,"area":null},{"id":"2504.19323","title":"NSFlow: An End-to-End FPGA Framework with Scalable Dataflow Architecture for Neuro-Symbolic AI","created":"2025-04-27","cited_by_count":1,"area":null},{"id":"2505.08981","title":"ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2404.16158","title":"The Feasibility of Implementing Large-Scale Transformers on Multi-FPGA Platforms","created":"2024-04-24","cited_by_count":0,"area":null},{"id":"2603.23668","title":"Energy Efficient Software Hardware CoDesign for Machine Learning: From TinyML to Large Language Models","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2605.06052","title":"XtraMAC: An Efficient MAC Architecture for Mixed-Precision LLM Inference on FPGA","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.25321","title":"LLMscope: Extracting LLM Assets from Edge AI Chips via Optical Probing","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.00106","title":"SyntheticHLS: Building Diverse Synthetic High-Level Synthesis Datasets using LLMs","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}