{"total":35,"rows":[{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"id":"2504.03360","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","created":"2025-04-04","cited_by_count":34,"area":null},{"id":"2502.11880","title":"Bitnet.cpp: Efficient Edge Inference for Ternary LLMs","created":"2025-02-17","cited_by_count":22,"area":null},{"id":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2410.16144","title":"1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs","created":"2024-10-21","cited_by_count":12,"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":"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":"2506.12040","title":"BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook","created":"2025-05-24","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":"2512.17970","title":"CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2510.15926","title":"TeLLMe v2: An Efficient End-to-End Ternary LLM Prefill and Decode Accelerator with Table-Lookup Matmul on Edge FPGAs","created":"2025-10-03","cited_by_count":2,"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":"2502.19008","title":"Binary Neural Networks for Large Language Model: A Survey","created":"2025-02-26","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":"2602.01027","title":"SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.20662","title":"TOM: A Ternary Read-only Memory Accelerator for LLM-powered Edge Intelligence","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2604.04523","title":"LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM","created":"2026-04-06","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":"2503.23817","title":"MVDRAM: Enabling GeMV Execution in Unmodified DRAM for Low-Bit LLM Acceleration","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2510.19482","title":"ELUTQ: Optimizing Quantization Accuracy under LUT-Based Computation for Edge LLMs","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2512.20623","title":"BitRL-Light: 1-bit LLM Agents with Deep Reinforcement Learning for Energy-Efficient Smart Home Lighting Optimization","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2602.22592","title":"pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.20913","title":"FairyFuse: Multiplication-Free LLM Inference on CPUs via Fused Ternary Kernels","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.06485","title":"Litespark Inference For CPUs: Ultra-Fast SIMD Framework for Ternary (1.58-bit) Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.08891","title":"PALUTE: Processing-In-Memory Acceleration via Lookup Table for Edge LLM Inference","created":"2026-06-08","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":"2607.14622","title":"ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.16391","title":"Where Post-Training Quantization Breaks Text Embedders: A Measured Map Across Four Embedder Families","created":"2026-09-14","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":"2609.32114","title":"Empowering Hybrid Attention Models on NPUs","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.00382","title":"On the Relationship between Model Quantization and Model Inversion Attacks","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}