{"total":472,"rows":[{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919,"area":null},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298,"area":null},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322,"area":null},{"id":"2302.04304","title":"Q-Diffusion: Quantizing Diffusion Models","created":"2023-02-08","cited_by_count":273,"area":"diffusion"},{"id":"2211.15736","title":"Post-training Quantization on Diffusion Models","created":"2022-11-28","cited_by_count":267,"area":"diffusion"},{"id":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119,"area":null},{"id":"2406.02540","title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","created":"2024-06-04","cited_by_count":115,"area":"diffusion"},{"id":"2304.07493","title":"OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization","created":"2023-04-15","cited_by_count":92,"area":null},{"id":"2406.02542","title":"Loki: Low-rank Keys for Efficient Sparse Attention","created":"2024-06-04","cited_by_count":89,"area":null},{"id":"2208.09225","title":"FP8 Quantization: The Power of the Exponent","created":"2022-08-19","cited_by_count":88,"area":null},{"id":"2306.15546","title":"When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions","created":"2023-06-27","cited_by_count":84,"area":null},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2405.16005","title":"PTQ4DiT: Post-training Quantization for Diffusion Transformers","created":"2024-05-25","cited_by_count":79,"area":"diffusion"},{"id":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77,"area":null},{"id":"2212.07048","title":"PD-Quant: Post-Training Quantization based on Prediction Difference Metric","created":"2022-12-14","cited_by_count":73,"area":null},{"id":"2312.05516","title":"Stateful Large Language Model Serving with Pensieve","created":"2023-12-09","cited_by_count":61,"area":"inference"},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2112.11312","title":"Implicit Neural Video Compression","created":"2021-12-21","cited_by_count":52,"area":null},{"id":"2208.14286","title":"ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization","created":"2022-08-30","cited_by_count":51,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2306.00317","title":"FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization","created":"2023-06-01","cited_by_count":48,"area":null},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"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":"2302.08469","title":"Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators","created":"2023-02-16","cited_by_count":43,"area":null},{"id":"2405.17873","title":"MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization","created":"2024-05-28","cited_by_count":43,"area":"diffusion"},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"area":"moe"},{"id":"2402.02446","title":"LQER: Low-Rank Quantization Error Reconstruction for LLMs","created":"2024-02-04","cited_by_count":41,"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":"2406.04333","title":"BitsFusion: 1.99 bits Weight Quantization of Diffusion Model","created":"2024-06-06","cited_by_count":37,"area":"diffusion"},{"id":"2201.13096","title":"SPDY: Accurate Pruning with Speedup Guarantees","created":"2022-01-31","cited_by_count":36,"area":null},{"id":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","cited_by_count":35,"area":null},{"id":"2312.07950","title":"CBQ: Cross-Block Quantization for Large Language Models","created":"2023-12-13","cited_by_count":34,"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":"2405.03144","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","created":"2024-05-06","cited_by_count":32,"area":null},{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","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":"2401.15865","title":"LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection","created":"2024-01-29","cited_by_count":29,"area":null},{"id":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2112.10769","title":"Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats","created":"2021-12-19","cited_by_count":26,"area":null},{"id":"2411.17713","title":"Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations","created":"2024-11-18","cited_by_count":26,"area":null},{"id":"2412.03131","title":"DiffKV: Differentiated Memory Management for Large Language Models with Parallel KV Compaction","created":"2024-12-04","cited_by_count":26,"area":"inference"},{"id":"2302.05397","title":"A Practical Mixed Precision Algorithm for Post-Training Quantization","created":"2023-02-10","cited_by_count":24,"area":null},{"id":"2406.02500","title":"Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques","created":"2024-06-04","cited_by_count":24,"area":"moe"},{"id":"2402.01749","title":"Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models","created":"2024-01-30","cited_by_count":23,"area":null},{"id":"2505.11497","title":"QVGen: Pushing the Limit of Quantized Video Generative Models","created":"2025-05-16","cited_by_count":22,"area":"diffusion"},{"id":"2509.25238","title":"PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases","created":"2025-09-25","cited_by_count":22,"area":"agents"},{"id":"2601.20088","title":"Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery","created":"2026-01-27","cited_by_count":22,"area":"mllm"},{"id":"2311.06322","title":"Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing","created":"2023-11-10","cited_by_count":21,"area":"diffusion"},{"id":"2405.14428","title":"Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2207.08338","title":"MobileCodec: Neural Inter-frame Video Compression on Mobile Devices","created":"2022-07-18","cited_by_count":19,"area":null},{"id":"2603.07685","title":"Scalable Training of Mixture-of-Experts Models with Megatron Core","created":"2026-03-08","cited_by_count":19,"area":"moe"},{"id":"2111.10302","title":"Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set","created":"2021-11-19","cited_by_count":18,"area":null},{"id":"2306.14052","title":"A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware","created":"2023-06-24","cited_by_count":18,"area":null},{"id":"2403.06082","title":"FrameQuant: Flexible Low-Bit Quantization for Transformers","created":"2024-03-10","cited_by_count":18,"area":null},{"id":"2406.05723","title":"Binarized Diffusion Model for Image Super-Resolution","created":"2024-06-09","cited_by_count":18,"area":"diffusion"},{"id":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17,"area":null},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2410.01723","title":"HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration","created":"2024-10-02","cited_by_count":17,"area":"diffusion"},{"id":"2411.17178","title":"LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization","created":"2024-11-26","cited_by_count":17,"area":null},{"id":"2506.16054","title":"PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models","created":"2025-06-19","cited_by_count":17,"area":null},{"id":"2205.12268","title":"Wavelet Feature Maps Compression for Image-to-Image CNNs","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16,"area":null},{"id":"2308.15987","title":"FPTQ: Fine-grained Post-Training Quantization for Large Language Models","created":"2023-08-30","cited_by_count":16,"area":null},{"id":"2310.04361","title":"Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion","created":"2023-10-06","cited_by_count":16,"area":"moe"},{"id":"2410.12032","title":"MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI","created":"2024-10-15","cited_by_count":16,"area":null},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2204.12322","title":"RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization","created":"2022-04-26","cited_by_count":15,"area":null},{"id":"2307.10638","title":"Quantized Feature Distillation for Network Quantization","created":"2023-07-20","cited_by_count":15,"area":"distill"},{"id":"2309.01729","title":"Softmax Bias Correction for Quantized Generative Models","created":"2023-09-04","cited_by_count":15,"area":"diffusion"},{"id":"2509.09090","title":"SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models","created":"2025-09-11","cited_by_count":15,"area":"vla"},{"id":"2202.00441","title":"Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction","created":"2022-02-01","cited_by_count":14,"area":null},{"id":"2202.07513","title":"Post-Training Quantization for Cross-Platform Learned Image Compression","created":"2022-02-15","cited_by_count":14,"area":null},{"id":"2311.16442","title":"Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization","created":"2023-11-28","cited_by_count":14,"area":null},{"id":"2407.11585","title":"QVD: Post-training Quantization for Video Diffusion Models","created":"2024-07-16","cited_by_count":14,"area":"diffusion"},{"id":"2310.01258","title":"MobileNVC: Real-time 1080p Neural Video Compression on a Mobile Device","created":"2023-10-02","cited_by_count":13,"area":null},{"id":"2407.03917","title":"Timestep-Aware Correction for Quantized Diffusion Models","created":"2024-07-04","cited_by_count":13,"area":"diffusion"},{"id":"2206.10844","title":"Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices","created":"2022-06-22","cited_by_count":12,"area":null},{"id":"2212.11138","title":"QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks","created":"2022-12-10","cited_by_count":12,"area":null},{"id":"2311.18130","title":"The Trifecta: Three simple techniques for training deeper Forward-Forward networks","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2405.07135","title":"Post Training Quantization of Large Language Models with Microscaling Formats","created":"2024-05-12","cited_by_count":12,"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":"2410.09615","title":"SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression","created":"2024-10-12","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":"2602.03051","title":"SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression","created":"2026-02-03","cited_by_count":12,"area":"mechinterp"},{"id":"2212.01330","title":"Device Interoperability for Learned Image Compression with Weights and Activations Quantization","created":"2022-12-02","cited_by_count":11,"area":null},{"id":"2406.12928","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","created":"2024-06-15","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":"2502.12346","title":"QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models","created":"2025-02-17","cited_by_count":11,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2506.01822","title":"GSCodec Studio: A Modular Framework for Gaussian Splat Compression","created":"2025-06-02","cited_by_count":11,"area":null},{"id":"2602.00135","title":"LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models","created":"2026-01-28","cited_by_count":11,"area":"mllm"},{"id":"2109.09113","title":"HPTQ: Hardware-Friendly Post Training Quantization","created":"2021-09-19","cited_by_count":10,"area":null},{"id":"2211.02854","title":"Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2308.07650","title":"EQ-Net: Elastic Quantization Neural Networks","created":"2023-08-15","cited_by_count":10,"area":null},{"id":"2309.06626","title":"Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity","created":"2023-09-12","cited_by_count":10,"area":null},{"id":"2407.11722","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","created":"2024-07-16","cited_by_count":10,"area":null}],"next_cursor":"100"}