{"total":52,"rows":[{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324,"area":null},{"id":"2310.11453","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","created":"2023-10-17","cited_by_count":189,"area":null},{"id":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"area":null},{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2406.03287","title":"SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"area":null},{"id":"2406.02528","title":"Scalable MatMul-free Language Modeling","created":"2024-06-04","cited_by_count":25,"area":null},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"area":null},{"id":"2306.16678","title":"BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models","created":"2023-06-29","cited_by_count":17,"area":null},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2306.06446","title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","created":"2023-06-10","cited_by_count":15,"area":"moe"},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2302.04907","title":"Binarized Neural Machine Translation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2305.14730","title":"BinaryViT: Towards Efficient and Accurate Binary Vision Transformers","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2306.01841","title":"Binary and Ternary Natural Language Generation","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2503.16134","title":"Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing","created":"2025-03-20","cited_by_count":7,"area":"ssm"},{"id":"2401.11851","title":"BETA: Binarized Energy-Efficient Transformer Accelerator at the Edge","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2409.15298","title":"Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model","created":"2024-09-04","cited_by_count":6,"area":null},{"id":"2301.00652","title":"Efficient Speech Representation Learning with Low-Bit Quantization","created":"2022-12-14","cited_by_count":5,"area":null},{"id":"2503.02394","title":"BHViT: Binarized Hybrid Vision Transformer","created":"2025-03-04","cited_by_count":5,"area":null},{"id":"2509.18968","title":"Otters: An Energy-Efficient SpikingTransformer via Optical Time-to-First-Spike Encoding","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2302.08571","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2305.07931","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","created":"2023-05-13","cited_by_count":4,"area":null},{"id":"2405.02543","title":"Exploring Extreme Quantization in Spiking Language Models","created":"2024-05-04","cited_by_count":4,"area":null},{"id":"2406.07247","title":"Dynamical Mean-Field Theory of Self-Attention Neural Networks","created":"2024-06-11","cited_by_count":4,"area":null},{"id":"2504.16269","title":"COBRA: Algorithm-Architecture Co-optimized Binary Transformer Accelerator for Edge Inference","created":"2025-04-22","cited_by_count":4,"area":null},{"id":"2509.22935","title":"Compute-Optimal Quantization-Aware Training","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2603.22370","title":"FAAR: Format-Aware Adaptive Rounding for NVFP4","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2409.05905","title":"Towards Narrowing the Generalization Gap in Deep Boolean Networks","created":"2024-09-06","cited_by_count":3,"area":null},{"id":"2605.17471","title":"WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2407.12070","title":"Co-Designing Binarized Transformer and Hardware Accelerator for Efficient End-to-End Edge Deployment","created":"2024-07-16","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":"2510.14823","title":"FraQAT: Quantization Aware Training with Fractional bits","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2602.13710","title":"HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models","created":"2026-02-14","cited_by_count":2,"area":"vla"},{"id":"2303.01166","title":"BPT: Binary Point Cloud Transformer for Place Recognition","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2403.09998","title":"FBPT: A Fully Binary Point Transformer","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2411.10346","title":"BiDense: Binarization for Dense Prediction","created":"2024-11-15","cited_by_count":1,"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":"2507.04456","title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2211.02292","title":"Boosting Binary Neural Networks via Dynamic Thresholds Learning","created":"2022-11-04","cited_by_count":0,"area":null},{"id":"2311.02772","title":"Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency","created":"2023-11-05","cited_by_count":0,"area":null},{"id":"2412.05225","title":"BEExformer: A Fast Inferencing Binarized Transformer with Early Exits","created":"2024-12-06","cited_by_count":0,"area":"inference"},{"id":"2502.00047","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","created":"2025-01-28","cited_by_count":0,"area":null},{"id":"2507.02222","title":"High-Fidelity Differential-information Driven Binary Vision Transformer","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2509.24425","title":"BiHDTrans: binary hyperdimensional transformer for efficient multivariate time series classification","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2601.02411","title":"SpikySpace: A Spiking State Space Model for Energy-Efficient Time Series Forecasting","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2601.22876","title":"Matterhorn: Masked Time-to-First-Spike Encoding by Reassigning the Silent State for Sparse and Energy-Efficient Spiking Transformers","created":"2026-01-30","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":"2606.13016","title":"Otters++: A Time-to-first-spike Based Energy Efficient Optical Spiking Transformer","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.27759","title":"Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks","created":"2026-06-26","cited_by_count":0,"area":null}],"next_cursor":null}