{"total":47,"rows":[{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2112.04267","title":"Implicit Neural Representations for Image Compression","created":"2021-12-08","cited_by_count":162,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2103.12369","title":"ReCU: Reviving the Dead Weights in Binary Neural Networks","created":"2021-03-23","cited_by_count":52,"area":null},{"id":"2110.06804","title":"A comprehensive review of Binary Neural Network","created":"2021-10-11","cited_by_count":45,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2302.05917","title":"Vector Quantized Wasserstein Auto-Encoder","created":"2023-02-12","cited_by_count":22,"area":null},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2209.01019","title":"On Quantizing Implicit Neural Representations","created":"2022-09-01","cited_by_count":20,"area":null},{"id":"2404.01847","title":"Accelerating Transformer Pre-training with 2:4 Sparsity","created":"2024-04-02","cited_by_count":19,"area":null},{"id":"2201.06515","title":"Differentiable Rule Induction with Learned Relational Features","created":"2022-01-17","cited_by_count":8,"area":null},{"id":"2107.03453","title":"$S^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks","created":"2021-07-07","cited_by_count":7,"area":null},{"id":"2211.11917","title":"Latent Iterative Refinement for Modular Source Separation","created":"2022-11-22","cited_by_count":7,"area":null},{"id":"2308.14152","title":"Unaligned 2D to 3D Translation with Conditional Vector-Quantized Code Diffusion using Transformers","created":"2023-08-27","cited_by_count":7,"area":null},{"id":"2410.15653","title":"Opportunities and Challenges of Generative-AI in Finance","created":"2024-10-21","cited_by_count":6,"area":null},{"id":"2504.06748","title":"Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate Representation","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2208.09708","title":"DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization","created":"2022-08-20","cited_by_count":5,"area":null},{"id":"2412.11471","title":"TrapFlow: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2110.01532","title":"Differentiable Spline Approximations","created":"2021-10-04","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":"2511.02652","title":"Differentiable Hierarchical Visual Tokenization","created":"2025-11-04","cited_by_count":4,"area":null},{"id":"2103.11284","title":"Learning Optimal Fronthauling and Decentralized Edge Computation in Fog Radio Access Networks","created":"2021-03-21","cited_by_count":3,"area":null},{"id":"2405.13155","title":"ReALLM: A general framework for LLM compression and fine-tuning","created":"2024-05-21","cited_by_count":3,"area":null},{"id":"2505.20646","title":"Binarized Neural Networks Converge Toward Algorithmic Simplicity: Empirical Support for the Learning-as-Compression Hypothesis","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2204.05805","title":"Learning to Express in Knowledge-Grounded Conversation","created":"2022-04-12","cited_by_count":2,"area":null},{"id":"2302.06513","title":"DEPAS: De-novo Pathology Semantic Masks using a Generative Model","created":"2023-02-13","cited_by_count":2,"area":null},{"id":"2412.05505","title":"Trimming Down Large Spiking Vision Transformers via Heterogeneous Quantization Search","created":"2024-12-07","cited_by_count":2,"area":null},{"id":"2510.08570","title":"Who Said Neural Networks Aren't Linear?","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2511.15300","title":"Quant-Trim in Practice: Improved Cross-Platform Low-Bit Deployment on Edge NPUs","created":"2025-11-19","cited_by_count":2,"area":null},{"id":"2601.15838","title":"TinySense: Effective CSI Compression for Scalable and Accurate Wi-Fi Sensing","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2605.13072","title":"Neural QAOA$^{2}$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.29128","title":"Apertus LLM Family Expansion via Distillation and Quantization","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2102.04379","title":"End-to-end Generative Zero-shot Learning via Few-shot Learning","created":"2021-02-08","cited_by_count":0,"area":null},{"id":"2202.09571","title":"Bit-wise Training of Neural Network Weights","created":"2022-02-19","cited_by_count":0,"area":null},{"id":"2206.12358","title":"Low- and Mixed-Precision Inference Accelerators","created":"2022-06-24","cited_by_count":0,"area":null},{"id":"2305.07341","title":"Model-based Programming: Redefining the Atomic Unit of Programming for the Deep Learning Era","created":"2023-05-12","cited_by_count":0,"area":null},{"id":"2311.09663","title":"Zenkai -- Framework For Exploring Beyond Backpropagation","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2503.02510","title":"Remote Sensing Image Classification Using Convolutional Neural Network (CNN) and Transfer Learning Techniques","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2505.00350","title":"Optimizing Deep Neural Networks using Safety-Guided Self Compression","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2505.17791","title":"Bruno: Backpropagation Running Undersampled for Novel device Optimization","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2505.22226","title":"Expressive yet Efficient Feature Expansion with Adaptive Cross-Hadamard Products","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2512.07142","title":"Winning the Lottery by Preserving Network Training Dynamics with Concrete Ticket Search","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2602.21662","title":"HybridINR-PCGC: Hybrid Lossless Point Cloud Geometry Compression Bridging Pretrained Model and Implicit Neural Representation","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.05172","title":"Trainable Bitwise Soft Quantization for Input Feature Compression","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.11589","title":"Toward Complex-Valued Neural Networks for Waveform Generation","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.18624","title":"Learning to Look Benign: Targeted Evasion of Malware Detectors via API Import Injection","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2608.25370","title":"CRAMER: Control via Request-Aware Masking for Editing Recommenders","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}