{"total":25,"rows":[{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"id":"2503.06862","title":"FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2510.10467","title":"AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2503.18002","title":"Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2","created":"2025-02-12","cited_by_count":8,"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":"2506.03781","title":"Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models","created":"2025-06-04","cited_by_count":5,"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":"2408.11939","title":"Matmul or No Matmul in the Era of 1-bit LLMs","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2505.22811","title":"Highly Efficient and Effective LLMs with Multi-Boolean Architectures","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2605.24144","title":"EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2504.01994","title":"PIM-LLM: A High-Throughput Hybrid PIM Architecture for 1-bit LLMs","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2506.17864","title":"QueueEDIT: Structural Self-Correction for Sequential Model Editing in LLMs","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2511.15369","title":"IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers","created":"2025-11-19","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":"2605.06082","title":"PoTAcc: A Pipeline for End-to-End Acceleration of Power-of-Two Quantized DNNs","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.26092","title":"GoQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2509.22512","title":"AxLLM: accelerator architecture for large language models with computation reuse capability","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2510.18650","title":"Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression","created":"2025-10-21","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":"2512.02403","title":"ESACT: An End-to-End Sparse Accelerator for Compute-Intensive Transformers via Local Similarity","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.04746","title":"SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2603.24595","title":"M2K: Making the Model-Kernel Interface Explicit for Reliable CUDA Kernel Verification","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.25306","title":"QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2608.01343","title":"DeVIT: Low-Power Vision Transformer Acceleration Using Delta Computation","created":"2026-08-02","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}],"next_cursor":null}