{"total":84,"rows":[{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"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":"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":"2405.06001","title":"LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit","created":"2024-05-09","cited_by_count":33,"area":"lr"},{"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":"2406.02528","title":"Scalable MatMul-free Language Modeling","created":"2024-06-04","cited_by_count":25,"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":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"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":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2502.06786","title":"Matryoshka Quantization","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2511.01815","title":"KV Cache Transform Coding for Compact Storage in LLM Inference","created":"2025-11-03","cited_by_count":13,"area":"inference"},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2505.11415","title":"MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems","created":"2025-05-16","cited_by_count":11,"area":"moe"},{"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":"2601.14888","title":"What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study","created":"2026-01-21","cited_by_count":10,"area":"lr"},{"id":"2605.22064","title":"Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild","created":"2026-05-21","cited_by_count":10,"area":null},{"id":"2505.00850","title":"ICQuant: Index Coding enables Low-bit LLM Quantization","created":"2025-05-01","cited_by_count":9,"area":null},{"id":"2508.19432","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2510.25817","title":"A Survey on Efficient Large Language Model Training: From Data-centric Perspectives","created":"2025-10-29","cited_by_count":9,"area":null},{"id":"2506.09104","title":"Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2405.15025","title":"OAC: Output-adaptive Calibration for Accurate Post-training Quantization","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2410.04808","title":"LPZero: Language Model Zero-cost Proxy Search from Zero","created":"2024-10-07","cited_by_count":7,"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":"2601.22709","title":"Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs","created":"2026-01-30","cited_by_count":6,"area":"mllm"},{"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":"2508.16785","title":"Interpreting the Effects of Quantization on LLMs","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2510.23926","title":"Improving the Straight-Through Estimator with Zeroth-Order Information","created":"2025-10-27","cited_by_count":5,"area":null},{"id":"2412.06858","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","created":"2024-12-08","cited_by_count":4,"area":"inference"},{"id":"2502.15779","title":"Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizer","created":"2025-02-17","cited_by_count":4,"area":"inference"},{"id":"2503.19353","title":"QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition","created":"2025-03-25","cited_by_count":4,"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":"2510.03267","title":"PT$^2$-LLM: Post-Training Ternarization for Large Language Models","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2510.21879","title":"TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge","created":"2025-10-23","cited_by_count":4,"area":"mllm"},{"id":"2603.01776","title":"FreeAct: Freeing Activations for LLM Quantization","created":"2026-03-02","cited_by_count":4,"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":"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":"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":"2507.16933","title":"SiLQ: Simple Large Language Model Quantization-Aware Training","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2510.13998","title":"BitNet Distillation","created":"2025-10-15","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":"2601.15287","title":"Towards Understanding Best Practices for Quantization of Vision-Language Models","created":"2026-01-21","cited_by_count":2,"area":"mllm"},{"id":"2601.19320","title":"StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths","created":"2026-01-27","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":"2608.12957","title":"I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization","created":"2026-08-13","cited_by_count":2,"area":"lr"},{"id":"2506.12038","title":"LCD: Advancing Extreme Low-Bit Clustering for Large Language Models via Knowledge Distillation","created":"2025-05-23","cited_by_count":1,"area":"distill"},{"id":"2507.04456","title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2510.11234","title":"Neural Weight Compression for Language Models","created":"2025-10-13","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":"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":"2605.08755","title":"LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2606.07116","title":"OffQ: Taming Structured Outliers in LLM Quantization by Offsetting","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2608.13966","title":"QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2609.39223","title":"QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2412.07067","title":"MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems","created":"2024-12-10","cited_by_count":0,"area":"moe"},{"id":"2503.05584","title":"QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution","created":"2025-03-07","cited_by_count":0,"area":"diffusion"},{"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":"2511.16653","title":"Teacher-Guided One-Shot Pruning via Context-Aware Knowledge Distillation","created":"2025-11-20","cited_by_count":0,"area":"distill"},{"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":"2512.04746","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":"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":"2601.09306","title":"On-Device Large Language Models for Sequential Recommendation","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2602.09130","title":"UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillation","created":"2026-02-09","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":"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":"2603.16867","title":"Efficient Reasoning on the Edge","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2604.19167","title":"LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation","created":"2026-04-21","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":"2605.20295","title":"Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization","created":"2026-05-19","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":"2608.24469","title":"Low-Rank Ternary Adaptation for Fine-Tuning Transformers","created":"2026-08-25","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":"2608.26581","title":"Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMs","created":"2026-08-27","cited_by_count":0,"area":"mllm"},{"id":"2609.26708","title":"Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning","created":"2026-09-22","cited_by_count":0,"area":"distill"},{"id":"2609.31009","title":"G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33601","title":"JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.14745","title":"SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.14934","title":"FidelityQ: Preserving Predictive Fidelity in Ultra-Low-Bit Language Model Quantization","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}