{"total":31,"rows":[{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440,"area":null},{"id":"2210.12316","title":"Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders","created":"2022-10-22","cited_by_count":112,"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":"2403.09673","title":"FoldToken: Learning Protein Language via Vector Quantization and Beyond","created":"2024-02-04","cited_by_count":23,"area":null},{"id":"2302.03213","title":"LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup","created":"2023-02-07","cited_by_count":20,"area":null},{"id":"2310.18608","title":"Embedding in Recommender Systems: A Survey","created":"2023-10-28","cited_by_count":20,"area":null},{"id":"2303.10126","title":"IRGen: Generative Modeling for Image Retrieval","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2303.04341","title":"Neural Vector Fields: Implicit Representation by Explicit Learning","created":"2023-03-08","cited_by_count":16,"area":null},{"id":"2201.11865","title":"FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients","created":"2022-01-28","cited_by_count":15,"area":null},{"id":"2311.15578","title":"Experimental Analysis of Large-scale Learnable Vector Storage Compression","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2208.05648","title":"Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graph","created":"2022-08-11","cited_by_count":10,"area":null},{"id":"2411.16550","title":"Representation Collapsing Problems in Vector Quantization","created":"2024-11-25","cited_by_count":10,"area":null},{"id":"2407.15540","title":"Differentiable Product Quantization for Memory Efficient Camera Relocalization","created":"2024-07-22","cited_by_count":9,"area":null},{"id":"2201.05409","title":"Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval","created":"2022-01-14","cited_by_count":7,"area":null},{"id":"2208.13571","title":"PECAN: A Product-Quantized Content Addressable Memory Network","created":"2022-08-13","cited_by_count":6,"area":null},{"id":"2104.07858","title":"Matching-oriented Product Quantization For Ad-hoc Retrieval","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2204.00281","title":"i-Razor: A Differentiable Neural Input Razor for Feature Selection and Dimension Search in DNN-Based Recommender Systems","created":"2022-04-01","cited_by_count":4,"area":null},{"id":"2309.17341","title":"MixQuant: Mixed Precision Quantization with a Bit-width Optimization Search","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2305.19435","title":"AdANNS: A Framework for Adaptive Semantic Search","created":"2023-05-30","cited_by_count":3,"area":null},{"id":"2411.01856","title":"MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2203.05082","title":"Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2309.01512","title":"Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2210.03282","title":"Set2Box: Similarity Preserving Representation Learning of Sets","created":"2022-10-07","cited_by_count":1,"area":null},{"id":"2311.10207","title":"Stella Nera: A Differentiable Maddness-Based Hardware Accelerator for Efficient Approximate Matrix Multiplication","created":"2023-11-16","cited_by_count":1,"area":null},{"id":"2603.17052","title":"Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2605.04084","title":"FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2108.09136","title":"Unsupervised Domain-adaptive Hash for Networks","created":"2021-08-20","cited_by_count":0,"area":null},{"id":"2311.06823","title":"Training A Multi-stage Deep Classifier with Feedback Signals","created":"2023-11-12","cited_by_count":0,"area":null},{"id":"2509.24431","title":"Semantic Compression via Multimodal Representation Learning","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2607.27475","title":"OneShot: Index-in-Ranking with Neural Scoring for Large-Scale Retrieval","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}