{"total":98,"rows":[{"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":"2411.02530","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","created":"2024-10-30","cited_by_count":36,"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":"2412.18653","title":"1.58-bit FLUX","created":"2024-12-24","cited_by_count":31,"area":null},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25,"area":null},{"id":"2510.24824","title":"Parallel Loop Transformer for Efficient Test-Time Computation Scaling","created":"2025-10-28","cited_by_count":24,"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":"2604.05550","title":"AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery","created":"2026-04-07","cited_by_count":23,"area":null},{"id":"2411.11745","title":"BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration","created":"2024-11-18","cited_by_count":18,"area":null},{"id":"2510.25602","title":"INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats","created":"2025-10-29","cited_by_count":18,"area":null},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","cited_by_count":17,"area":null},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"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":"2502.06786","title":"Matryoshka Quantization","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2410.05265","title":"PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization","created":"2024-10-07","cited_by_count":12,"area":null},{"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":"2509.09679","title":"ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms","created":"2025-09-11","cited_by_count":10,"area":null},{"id":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","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":"2506.11784","title":"GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers","created":"2025-06-13","cited_by_count":8,"area":null},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"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":"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":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2505.18724","title":"LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning","created":"2025-05-24","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":"2508.05571","title":"iFairy: the First 2-bit Complex LLM with All Parameters in $\\{\\pm1, \\pm i\\}$","created":"2025-08-07","cited_by_count":5,"area":null},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"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":"2509.22935","title":"Compute-Optimal Quantization-Aware Training","created":"2025-09-26","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":"2602.08923","title":"DynamiQ: Accelerating Gradient Synchronization using Compressed Multi-hop All-reduce","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2603.01776","title":"FreeAct: Freeing Activations for LLM Quantization","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2411.06360","title":"An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks","created":"2024-11-10","cited_by_count":3,"area":null},{"id":"2501.11847","title":"A Survey on Memory-Efficient Transformer-Based Model Training in AI for Science","created":"2025-01-21","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":"2509.00031","title":"End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost","created":"2025-08-21","cited_by_count":3,"area":null},{"id":"2606.10531","title":"LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization","created":"2026-06-09","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":"2505.11982","title":"FedHQ: Hybrid Runtime Quantization for Federated Learning","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2506.01967","title":"Turning LLM Activations Quantization-Friendly","created":"2025-05-11","cited_by_count":2,"area":null},{"id":"2510.13998","title":"BitNet Distillation","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2512.02901","title":"Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in $\\{\\pm 1, \\pm i\\}$","created":"2025-12-02","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":"2601.19320","title":"StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2601.22787","title":"Float8@2bits: Entropy Coding Enables Data-Free Model Compression","created":"2026-01-30","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":"2602.02680","title":"FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment","created":"2026-02-02","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":"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":"2605.29756","title":"LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.04050","title":"LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection","created":"2026-06-02","cited_by_count":2,"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":"2505.17595","title":"NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2508.03760","title":"FlashCommunication V2: Bit Splitting and Spike Reserving for Any Bit Communication","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2509.03472","title":"DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2510.04066","title":"QuantDemoire: Quantization with Outlier Aware for Image Demoir\\'eing","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2510.13832","title":"Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2511.13147","title":"OTARo: Once Tuning for All Precisions toward Robust On-Device LLMs","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2601.14549","title":"QMC: Efficient SLM Edge Inference via Outlier-Aware Quantization and Emergent Memories Co-Design","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2602.01027","title":"SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models","created":"2026-02-01","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":"2604.00529","title":"MF-QAT: Multi-Format Quantization-Aware Training for Elastic Inference","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.16423","title":"Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.31124","title":"QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2608.07019","title":"ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.26926","title":"A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.04526","title":"Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs","created":"2026-09-03","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":"2407.15508","title":"Compensate Quantization Errors+: Quantized Models Are Inquisitive Learners","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2505.18758","title":"Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2509.26277","title":"Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation","created":"2025-09-30","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":"2512.19069","title":"Can abstract concepts from LLM improve SLM performance?","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2601.07878","title":"Sliced-Wasserstein Distribution Alignment Loss Improves the Ultra-Low-Bit Quantization of Large Language Models","created":"2026-01-11","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":"2602.20646","title":"On the Convergence of Stochastic Gradient Descent with Perturbed Forward-Backward Passes","created":"2026-02-24","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":"2604.24273","title":"BitRL: Reinforcement Learning with 1-bit Quantized Language Models for Resource-Constrained Edge Deployment","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.05819","title":"HCInfer: An Efficient Inference System via Error Compensation for Resource-Constrained Devices","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.10655","title":"BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.10673","title":"Compander-Aligned Query Geometry for Quantized Zeroth-Order Optimization","created":"2026-05-11","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":"2606.00539","title":"GNMR: Runtime Stability Control for Low-Precision Large Language Model Training","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.25674","title":"BitNet Text Embeddings","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.10855","title":"Reliability Scaling Laws for Quantized Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.18284","title":"Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2608.03919","title":"Low-Dimensional High-Leverage Subspace Optimization: Beyond Full-Parameter Coupled Training for Neural Network Quantization","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.14149","title":"QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.15567","title":"SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantization","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.00049","title":"REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent","created":"2026-08-30","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":"2609.36654","title":"Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference","created":"2026-09-29","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},{"id":"2610.19189","title":"Adaptive Computation with Conformal Certification","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}