{"total":83,"rows":[{"id":"2403.15388","title":"LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models","created":"2024-03-22","cited_by_count":402,"area":"lr"},{"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":"2312.05821","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","created":"2023-12-10","cited_by_count":169,"area":"inference"},{"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":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2402.04291","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","created":"2024-02-06","cited_by_count":144,"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":"2411.15024","title":"DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models","created":"2024-11-22","cited_by_count":96,"area":"inference"},{"id":"2405.16005","title":"PTQ4DiT: Post-training Quantization for Diffusion Transformers","created":"2024-05-25","cited_by_count":79,"area":"diffusion"},{"id":"2404.14047","title":"An empirical study of LLaMA3 quantization: from LLMs to MLLMs","created":"2024-04-22","cited_by_count":64,"area":"mllm"},{"id":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"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":"2410.06270","title":"Mixture Compressor for Mixture-of-Experts LLMs Gains More","created":"2024-10-08","cited_by_count":41,"area":"moe"},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2407.04752","title":"SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking","created":"2024-07-05","cited_by_count":31,"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":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2406.07177","title":"TernaryLLM: Ternarized Large Language Model","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"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":"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":"2411.11843","title":"Bi-Mamba: Towards Accurate 1-Bit State Space Models","created":"2024-11-18","cited_by_count":12,"area":"ssm"},{"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":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2409.16997","title":"INT-FlashAttention: Enabling Flash Attention for INT8 Quantization","created":"2024-09-25","cited_by_count":9,"area":null},{"id":"2411.15446","title":"freePruner: A Training-free Approach for Large Multimodal Model Acceleration","created":"2024-11-23","cited_by_count":8,"area":"mllm"},{"id":"2405.15025","title":"OAC: Output-adaptive Calibration for Accurate Post-training Quantization","created":"2024-05-23","cited_by_count":7,"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":"2503.16134","title":"Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing","created":"2025-03-20","cited_by_count":7,"area":"ssm"},{"id":"2504.07389","title":"Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression","created":"2025-04-10","cited_by_count":7,"area":null},{"id":"2503.15465","title":"FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers","created":"2025-03-19","cited_by_count":6,"area":"diffusion"},{"id":"2604.18556","title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","created":"2026-04-20","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":"2505.02413","title":"Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks","created":"2025-05-05","cited_by_count":5,"area":"mllm"},{"id":"2507.07580","title":"COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2509.18763","title":"Bi-VLM: Pushing Ultra-Low Precision Post-Training Quantization Boundaries in Vision-Language Models","created":"2025-09-23","cited_by_count":5,"area":"mllm"},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2507.01027","title":"DBellQuant: Breaking the Bell with Double-Bell Transformation for LLMs Post Training Binarization","created":"2025-06-18","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":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2410.14570","title":"Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs","created":"2024-10-18","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":"2509.23729","title":"LUQ: Layerwise Ultra-Low Bit Quantization for Multimodal Large Language Models","created":"2025-09-28","cited_by_count":3,"area":"mllm"},{"id":"2602.17698","title":"ScaleBITS: Scalable Bitwidth Search for Hardware-Aligned Mixed-Precision LLMs","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2409.11650","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","created":"2024-09-18","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":"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":"2510.10962","title":"MC#: Mixture Compressor for Mixture-of-Experts Large Models","created":"2025-10-13","cited_by_count":2,"area":"mllm"},{"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":"2606.10520","title":"UniSVQ: 2-bit Unified Scalar-Vector Quantization","created":"2026-06-09","cited_by_count":2,"area":"inference"},{"id":"2402.10474","title":"One-Bit Quantization and Sparsification for Multiclass Linear Classification with Strong Regularization","created":"2024-02-16","cited_by_count":1,"area":null},{"id":"2501.18154","title":"Mixed-Precision Graph Neural Quantization for Low Bit Large Language Models","created":"2025-01-30","cited_by_count":1,"area":null},{"id":"2504.19746","title":"FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2507.18073","title":"Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method","created":"2025-07-24","cited_by_count":1,"area":null},{"id":"2508.06974","title":"Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models","created":"2025-08-09","cited_by_count":1,"area":"lr"},{"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":"2510.26690","title":"LoRAQuant: Mixed-Precision Quantization of LoRA to Ultra-Low Bits","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2604.10603","title":"MoEITS: A Green AI approach for simplifying MoE-LLMs","created":"2026-04-12","cited_by_count":1,"area":"moe"},{"id":"2607.01876","title":"SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models","created":"2026-07-02","cited_by_count":1,"area":"mllm"},{"id":"2405.14597","title":"Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2411.01611","title":"Stochastic Communication Avoidance for Recommendation Systems","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2501.12896","title":"Irrational Complex Rotations Empower Low-bit Optimizers","created":"2025-01-22","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":"2512.21651","title":"Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models","created":"2025-12-25","cited_by_count":0,"area":"lr"},{"id":"2604.03957","title":"BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design","created":"2026-04-05","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":"2605.17985","title":"SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.05429","title":"Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.10803","title":"Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.14181","title":"Quantize with Confidence? An Empirical Study of Quantization for Code Generation","created":"2026-07-15","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":"2609.38521","title":"ShamAN-Q: Shampoo Augmented NanoQuant for Sub-1-bit LLM Weights","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.06026","title":"Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.09202","title":"Few Bits, One Law: Toward W2A4KV2","created":"2026-10-06","cited_by_count":0,"area":"inference"},{"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}