{"total":145,"rows":[{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435,"area":null},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324,"area":null},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278,"area":null},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181,"area":null},{"id":"2203.05740","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","created":"2022-03-11","cited_by_count":180,"area":null},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170,"area":null},{"id":"2112.04267","title":"Implicit Neural Representations for Image Compression","created":"2021-12-08","cited_by_count":162,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"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":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139,"area":"inference"},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119,"area":null},{"id":"2203.07259","title":"The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models","created":"2022-03-14","cited_by_count":115,"area":"inference"},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2304.13013","title":"Stable and low-precision training for large-scale vision-language models","created":"2023-04-25","cited_by_count":75,"area":"mllm"},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2306.09818","title":"HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation","created":"2023-06-16","cited_by_count":71,"area":null},{"id":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"area":null},{"id":"2304.06632","title":"AI-Generated Content (AIGC): A Survey","created":"2023-03-26","cited_by_count":59,"area":null},{"id":"2409.17066","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":57,"area":null},{"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":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2212.14593","title":"NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise Modeling","created":"2022-12-30","cited_by_count":51,"area":null},{"id":"2306.07050","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","created":"2023-06-12","cited_by_count":50,"area":"inference"},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"area":null},{"id":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","cited_by_count":31,"area":null},{"id":"2309.15848","title":"SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations","created":"2023-09-27","cited_by_count":31,"area":null},{"id":"2409.07414","title":"NVRC: Neural Video Representation Compression","created":"2024-09-11","cited_by_count":29,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2402.13720","title":"Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding","created":"2024-02-21","cited_by_count":25,"area":"inference"},{"id":"2308.09723","title":"FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs","created":"2023-08-16","cited_by_count":22,"area":"moe"},{"id":"2204.10878","title":"ChapterBreak: A Challenge Dataset for Long-Range Language Models","created":"2022-04-22","cited_by_count":18,"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":"2101.05938","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","created":"2021-01-15","cited_by_count":15,"area":"distill"},{"id":"2305.06559","title":"Patch-wise Mixed-Precision Quantization of Vision Transformer","created":"2023-05-11","cited_by_count":15,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2112.06126","title":"Neural Network Quantization for Efficient Inference: A Survey","created":"2021-12-08","cited_by_count":14,"area":null},{"id":"2204.04705","title":"SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems","created":"2022-04-10","cited_by_count":14,"area":null},{"id":"2303.01980","title":"Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle","created":"2023-02-05","cited_by_count":14,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2112.11594","title":"GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design","created":"2021-12-22","cited_by_count":13,"area":null},{"id":"2203.14380","title":"Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection","created":"2022-03-27","cited_by_count":13,"area":null},{"id":"2206.01838","title":"Differentially Private Model Compression","created":"2022-06-03","cited_by_count":13,"area":null},{"id":"2402.01596","title":"Immersive Video Compression using Implicit Neural Representations","created":"2024-02-02","cited_by_count":12,"area":null},{"id":"2105.03343","title":"Adapting by Pruning: A Case Study on BERT","created":"2021-05-07","cited_by_count":11,"area":null},{"id":"2311.11420","title":"LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms","created":"2023-11-19","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":"2103.06231","title":"Quantization-Guided Training for Compact TinyML Models","created":"2021-03-10","cited_by_count":10,"area":null},{"id":"2201.05842","title":"UDC: Unified DNAS for Compressible TinyML Models","created":"2022-01-15","cited_by_count":10,"area":null},{"id":"2203.13483","title":"MKQ-BERT: Quantized BERT with 4-bits Weights and Activations","created":"2022-03-25","cited_by_count":10,"area":null},{"id":"2501.02173","title":"The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit","created":"2025-01-04","cited_by_count":10,"area":"inference"},{"id":"2307.07705","title":"CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal Devices","created":"2023-07-15","cited_by_count":9,"area":null},{"id":"2102.07725","title":"Neural Network Compression for Noisy Storage Devices","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2305.09098","title":"Weight-Inherited Distillation for Task-Agnostic BERT Compression","created":"2023-05-16","cited_by_count":8,"area":"distill"},{"id":"2105.12676","title":"Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale","created":"2021-05-26","cited_by_count":7,"area":null},{"id":"2111.06503","title":"AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator","created":"2021-11-10","cited_by_count":7,"area":null},{"id":"2306.01841","title":"Binary and Ternary Natural Language Generation","created":"2023-06-02","cited_by_count":7,"area":null},{"id":"2104.08323","title":"Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators","created":"2021-04-16","cited_by_count":6,"area":null},{"id":"2208.08562","title":"Restructurable Activation Networks","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2210.12924","title":"OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2212.08663","title":"Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2208.00164","title":"Distilled Low Rank Neural Radiance Field with Quantization for Light Field Compression","created":"2022-07-30","cited_by_count":5,"area":null},{"id":"2301.00652","title":"Efficient Speech Representation Learning with Low-Bit Quantization","created":"2022-12-14","cited_by_count":5,"area":null},{"id":"2503.15748","title":"PARQ: Piecewise-Affine Regularized Quantization","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2203.03794","title":"YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers","created":"2022-03-08","cited_by_count":4,"area":null},{"id":"2203.09055","title":"Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT","created":"2022-03-17","cited_by_count":4,"area":null},{"id":"2205.06287","title":"Adaptive Block Floating-Point for Analog Deep Learning Hardware","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2212.12653","title":"Hyperspherical Quantization: Toward Smaller and More Accurate Models","created":"2022-12-24","cited_by_count":4,"area":null},{"id":"2308.04269","title":"Lossy and Lossless (L$^2$) Post-training Model Size Compression","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2309.00964","title":"eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2310.03661","title":"Robustness-Guided Image Synthesis for Data-Free Quantization","created":"2023-10-05","cited_by_count":4,"area":null},{"id":"2202.09009","title":"LG-LSQ: Learned Gradient Linear Symmetric Quantization","created":"2022-02-18","cited_by_count":3,"area":null},{"id":"2207.11048","title":"Quantized Sparse Weight Decomposition for Neural Network Compression","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2212.02634","title":"QFT: Post-training quantization via fast joint finetuning of all degrees of freedom","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2303.01277","title":"Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication","created":"2023-03-02","cited_by_count":3,"area":null},{"id":"2304.00717","title":"MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model","created":"2023-04-03","cited_by_count":3,"area":null},{"id":"2312.07342","title":"Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2401.01369","title":"RL-MPCA: A Reinforcement Learning Based Multi-Phase Computation Allocation Approach for Recommender Systems","created":"2023-12-27","cited_by_count":3,"area":null},{"id":"2403.17154","title":"On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2410.09324","title":"Token Pruning using a Lightweight Background Aware Vision Transformer","created":"2024-10-12","cited_by_count":3,"area":"inference"},{"id":"2509.05584","title":"ProfilingAgent: Profiling-Guided Agentic Reasoning for Adaptive Model Optimization","created":"2025-09-06","cited_by_count":3,"area":"lr"},{"id":"2603.07789","title":"SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2605.12464","title":"Search Your Block Floating Point Scales!","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2605.17471","title":"WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2108.13465","title":"Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2204.02227","title":"SD-Conv: Towards the Parameter-Efficiency of Dynamic Convolution","created":"2022-04-05","cited_by_count":2,"area":null},{"id":"2205.06929","title":"ImageSig: A signature transform for ultra-lightweight image recognition","created":"2022-05-13","cited_by_count":2,"area":null},{"id":"2210.13086","title":"Legal-Tech Open Diaries: Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2303.01505","title":"Ternary Quantization: A Survey","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2304.04518","title":"Are Visual Recognition Models Robust to Image Compression?","created":"2023-04-10","cited_by_count":2,"area":null},{"id":"2307.05972","title":"Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models","created":"2023-07-12","cited_by_count":2,"area":null},{"id":"2307.06143","title":"Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression","created":"2023-07-12","cited_by_count":2,"area":null}],"next_cursor":"100"}