{"total":144,"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":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"area":"safety"},{"id":"2503.12340","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","created":"2025-03-16","cited_by_count":67,"area":null},{"id":"2404.02657","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models","created":"2024-04-03","cited_by_count":65,"area":"lr"},{"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":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"id":"2504.02692","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","created":"2025-04-03","cited_by_count":60,"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":"2504.03360","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","created":"2025-04-04","cited_by_count":34,"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":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","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":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2411.02829","title":"CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration","created":"2024-11-05","cited_by_count":25,"area":null},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25,"area":null},{"id":"2508.14896","title":"Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs","created":"2025-08-20","cited_by_count":23,"area":null},{"id":"2408.08554","title":"ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models","created":"2024-08-16","cited_by_count":22,"area":"inference"},{"id":"2410.05589","title":"ParallelSpec: Parallel Drafter for Efficient Speculative Decoding","created":"2024-10-08","cited_by_count":22,"area":"inference"},{"id":"2505.02214","title":"An Empirical Study of Qwen3 Quantization","created":"2025-05-04","cited_by_count":21,"area":null},{"id":"2504.09724","title":"A Survey on Efficient Vision-Language Models","created":"2025-04-13","cited_by_count":19,"area":"mllm"},{"id":"2411.17691","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","created":"2024-11-26","cited_by_count":18,"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":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2508.01625","title":"EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models","created":"2025-08-03","cited_by_count":18,"area":"moe"},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2410.17711","title":"Beware of Calibration Data for Pruning Large Language Models","created":"2024-10-23","cited_by_count":15,"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":"2509.12019","title":"AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models","created":"2025-09-15","cited_by_count":14,"area":null},{"id":"2604.22748","title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","created":"2026-04-24","cited_by_count":14,"area":"wm"},{"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":"2510.03274","title":"Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models","created":"2025-09-27","cited_by_count":12,"area":null},{"id":"2404.05662","title":"BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models","created":"2024-04-08","cited_by_count":11,"area":"diffusion"},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2412.01380","title":"Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking","created":"2024-12-02","cited_by_count":11,"area":"inference"},{"id":"2412.05926","title":"BiDM: Pushing the Limit of Quantization for Diffusion Models","created":"2024-12-08","cited_by_count":11,"area":"diffusion"},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2409.16997","title":"INT-FlashAttention: Enabling Flash Attention for INT8 Quantization","created":"2024-09-25","cited_by_count":9,"area":null},{"id":"2503.06862","title":"FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables","created":"2025-03-10","cited_by_count":9,"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":"2502.13179","title":"PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models","created":"2025-02-18","cited_by_count":8,"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":"2407.14417","title":"Mixture of Experts with Mixture of Precisions for Tuning Quality of Service","created":"2024-07-19","cited_by_count":7,"area":"moe"},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","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":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","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":"2504.07389","title":"Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression","created":"2025-04-10","cited_by_count":7,"area":null},{"id":"2505.20112","title":"ERC-SVD: Error-Controlled SVD for Large Language Model Compression","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2605.23078","title":"GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs","created":"2026-05-21","cited_by_count":7,"area":"moe"},{"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":"2412.17560","title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","created":"2024-12-23","cited_by_count":5,"area":null},{"id":"2501.16385","title":"FBQuant: FeedBack Quantization for Large Language Models","created":"2025-01-25","cited_by_count":5,"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":"2505.23966","title":"FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression","created":"2025-05-29","cited_by_count":5,"area":"inference"},{"id":"2506.07627","title":"Event-Priori-Based Vision-Language Model for Efficient Visual Understanding","created":"2025-06-09","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":"2508.03332","title":"Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models","created":"2025-08-05","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":"2605.00422","title":"BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2407.02891","title":"GPTQT: Quantize Large Language Models Twice to Push the Efficiency","created":"2024-07-03","cited_by_count":4,"area":null},{"id":"2410.19103","title":"TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2506.12040","title":"BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook","created":"2025-05-24","cited_by_count":4,"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":"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":"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":"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":"2510.04595","title":"SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba","created":"2025-10-06","cited_by_count":3,"area":"ssm"},{"id":"2601.21933","title":"Just Noticeable Difference Modeling for Deep Visual Features","created":"2026-01-29","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":"2505.22811","title":"Highly Efficient and Effective LLMs with Multi-Boolean Architectures","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.05664","title":"BAQ: Efficient Bit Allocation Quantization for Large Language Models","created":"2025-06-06","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":"2507.08765","title":"Compress Any Segment Anything Model (SAM)","created":"2025-07-11","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":"2602.04163","title":"BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models","created":"2026-02-04","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":"2604.06798","title":"MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization","created":"2026-04-08","cited_by_count":2,"area":"moe"},{"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":"2606.10520","title":"UniSVQ: 2-bit Unified Scalar-Vector Quantization","created":"2026-06-09","cited_by_count":2,"area":"inference"},{"id":"2609.06161","title":"All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs","created":"2026-09-05","cited_by_count":2,"area":null},{"id":"2405.13358","title":"AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs","created":"2024-05-22","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":"2503.13089","title":"ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2504.05352","title":"Achieving binary weight and activation for LLMs using Post-Training Quantization","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2505.08620","title":"Resource-Efficient Language Models: Quantization for Fast and Accessible Inference","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2505.15909","title":"Is (Selective) Round-To-Nearest Quantization All You Need?","created":"2025-05-21","cited_by_count":1,"area":null}],"next_cursor":"100"}