{"total":19,"rows":[{"id":"2509.23809","title":"Tequila: Trapping-free Ternary Quantization for Large Language Models","created":"2025-09-28","cited_by_count":9,"area":null},{"id":"2509.13765","title":"TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2601.07892","title":"Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification","created":"2026-01-12","cited_by_count":5,"area":null},{"id":"2504.08378","title":"Scaling Up On-Device LLMs via Active-Weight Swapping Between DRAM and Flash","created":"2025-04-11","cited_by_count":4,"area":null},{"id":"2510.03267","title":"PT$^2$-LLM: Post-Training Ternarization for Large Language Models","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2511.13676","title":"T-SAR: A Full-Stack Co-design for CPU-Only Ternary LLM Inference via In-Place SIMD ALU Reorganization","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2511.21910","title":"Platinum: Path-Adaptable LUT-Based Accelerator Tailored for Low-Bit Weight Matrix Multiplication","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2512.02901","title":"Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in $\\{\\pm 1, \\pm i\\}$","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2512.06443","title":"Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2504.03387","title":"BitHEP -- The Limits of Low-Precision ML in HEP","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2508.06753","title":"Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Models","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2606.03026","title":"Spike-Aware INT8 Execution for Spiking Language Models on Commodity CPUs","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2609.16338","title":"Breaking the 1.58-bit Barrier for Ternary LLMs","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2603.25813","title":"MAGNET: Autonomous Expert Model Generation via Decentralized Autoresearch and BitNet Training","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2607.14618","title":"PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.26206","title":"Ankhdjet: An Open-Source Compiler for Mask-Programmed Ternary Compute-in-ROM on an Open PDK","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.00224","title":"QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.27453","title":"Implementation and Evaluation of BitNet Inference on a CGLA by Signed-Int4 Instructions","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.08403","title":"SSR: Sparse Segment Reduction for Ternary GEMM Acceleration","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}