{"total":29,"rows":[{"id":"2505.18659","title":"Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2509.16989","title":"PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models","created":"2025-09-21","cited_by_count":9,"area":null},{"id":"2509.23809","title":"Tequila: Trapping-free Ternary Quantization for Large Language Models","created":"2025-09-28","cited_by_count":9,"area":null},{"id":"2509.11177","title":"Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs","created":"2025-09-14","cited_by_count":6,"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":"2508.05571","title":"iFairy: the First 2-bit Complex LLM with All Parameters in $\\{\\pm1, \\pm i\\}$","created":"2025-08-07","cited_by_count":5,"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":"2510.05288","title":"DP-Adam-AC: Privacy-preserving Fine-Tuning of Localizable Language Models Using Adam Optimization with Adaptive Clipping","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2604.07888","title":"Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2606.10531","title":"LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization","created":"2026-06-09","cited_by_count":3,"area":null},{"id":"2510.13998","title":"BitNet Distillation","created":"2025-10-15","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":"2505.17701","title":"COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection","created":"2025-05-23","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":"2605.00320","title":"VitaLLM: A Versatile and Tiny Accelerator for Mixed-Precision LLM Inference on Edge Devices","created":"2026-05-01","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":"2607.23390","title":"When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation","created":"2026-07-25","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":"2609.33548","title":"TerMeZO: Ternary Sparse Zeroth-Order Optimization for Fine-tuning BitNet Models at the Edge","created":"2026-09-27","cited_by_count":1,"area":null},{"id":"2505.15835","title":"Transforming Decoder-Only Transformers for Accurate WiFi-Telemetry Based Indoor Localization","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.00528","title":"Ultra-Quantisation: Efficient Embedding Search via 1.58-bit Encodings","created":"2025-05-31","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":"2606.25674","title":"BitNet Text Embeddings","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.24469","title":"Low-Rank Ternary Adaptation for Fine-Tuning Transformers","created":"2026-08-25","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":"2609.27453","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":"2609.37416","title":"Scale Sensitivity in Low-Bit Post-Training Quantization: Curvature of the Quantization Error Landscape","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.07853","title":"Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}