{"total":70,"rows":[{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243,"area":null},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"id":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"id":"2407.00088","title":"T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge","created":"2024-06-25","cited_by_count":55,"area":null},{"id":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31,"area":null},{"id":"2410.03129","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","created":"2024-10-04","cited_by_count":31,"area":null},{"id":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22,"area":null},{"id":"2502.07780","title":"DarwinLM: Evolutionary Structured Pruning of Large Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2406.12311","title":"Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2506.09397","title":"SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving","created":"2025-06-11","cited_by_count":13,"area":null},{"id":"2407.07093","title":"FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2502.14816","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","created":"2025-02-20","cited_by_count":10,"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":"2412.09282","title":"CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2412.04787","title":"Direct Quantized Training of Language Models with Stochastic Rounding","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2511.13061","title":"MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity","created":"2025-11-17","cited_by_count":6,"area":null},{"id":"2606.26650","title":"CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs","created":"2026-06-25","cited_by_count":6,"area":null},{"id":"2502.01705","title":"Progressive Binarization with Semi-Structured Pruning for LLMs","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2603.25284","title":"SliderQuant: Accurate Post-Training Quantization for LLMs","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2503.03777","title":"FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference","created":"2025-03-04","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":"2512.00862","title":"HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs","created":"2025-11-30","cited_by_count":4,"area":null},{"id":"2501.18596","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2504.13932","title":"Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2505.11076","title":"Addition is almost all you need: Compressing large language models with double binary factorization","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2603.28845","title":"OneComp: One-Line Revolution for Generative AI Model Compression","created":"2026-03-30","cited_by_count":3,"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":"2506.11044","title":"Boost Post-Training Quantization via Null Space Optimization for Large Language Models","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.20251","title":"Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2510.19498","title":"Energy-Efficient and Dequantization-Free Q-LLMs: A Spiking Neural Network Approach to Salient Value Mitigation","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2602.02546","title":"D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2605.04062","title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2405.17233","title":"CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMs","created":"2024-05-27","cited_by_count":1,"area":null},{"id":"2410.01309","title":"Getting Free Bits Back from Rotational Symmetries in LLMs","created":"2024-10-02","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":"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":"2508.19087","title":"APT-LLM: Exploiting Arbitrary-Precision Tensor Core Computing for LLM Acceleration","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.03275","title":"SDQ-LLM: Sigma-Delta Quantization for 1-bit LLMs of any size","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2601.22716","title":"Breaking the Blocks: Continuous Low-Rank Decomposed Scaling for Unified LLM Quantization and Adaptation","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.06694","title":"NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.07374","title":"TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.08817","title":"Kirin: Improving ANN efficiency with SNN Hybridization","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2605.08894","title":"Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2407.00467","title":"VcLLM: Video Codecs are Secretly Tensor Codecs","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2407.15545","title":"Inverted Activations: Reducing Memory Footprint in Neural Network Training","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2410.06973","title":"Personal Intelligence System UniLM: Hybrid On-Device Small Language Model and Server-Based Large Language Model for Malay Nusantara","created":"2024-10-09","cited_by_count":0,"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":"2511.21736","title":"R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.14481","title":"SASQ: Static Activation Scaling for Quantization-Aware Training in Large Language Models","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.00377","title":"DecompressionLM: Deterministic, Diagnostic, and Zero-Shot Concept Graph Extraction from Language Models","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.05367","title":"RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.00042","title":"LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment","created":"2026-02-09","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":"2605.24058","title":"Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.25674","title":"BitNet Text Embeddings","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.08643","title":"BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.10855","title":"Reliability Scaling Laws for Quantized Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.14630","title":"Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.05240","title":"One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.09595","title":"From Sweep to Seam: Interleaved Cross-Block Post-Training Quantization","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.25977","title":"When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.38521","title":"ShamAN-Q: Shampoo Augmented NanoQuant for Sub-1-bit LLM Weights","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}