{"total":20,"rows":[{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2411.16550","title":"Representation Collapsing Problems in Vector Quantization","created":"2024-11-25","cited_by_count":10,"area":null},{"id":"2501.03078","title":"Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks","created":"2025-01-06","cited_by_count":8,"area":null},{"id":"2410.15017","title":"DM-Codec: Distilling Multimodal Representations for Speech Tokenization","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2407.04939","title":"Balance of Number of Embedding and their Dimensions in Vector Quantization","created":"2024-07-06","cited_by_count":4,"area":null},{"id":"2405.14222","title":"Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2510.12721","title":"CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2605.24144","title":"EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2402.04713","title":"Theoretical and Empirical Analysis of Adaptive Entry Point Selection for Graph-based Approximate Nearest Neighbor Search","created":"2024-02-07","cited_by_count":1,"area":null},{"id":"2412.00369","title":"Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding","created":"2024-11-30","cited_by_count":1,"area":null},{"id":"2501.10479","title":"Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2502.16931","title":"Machine learning and high dimensional vector search","created":"2025-02-24","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":"2606.12876","title":"Multi-Bitwidth Quantization for LLMs Using Additive Codebooks","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2508.09090","title":"SPARC: Soft Probabilistic Adaptive multi-interest Retrieval Model via Codebooks for recommender system","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2508.15372","title":"Image-Conditioned 3D Gaussian Splat Quantization","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2508.15436","title":"PLASMA: A Layout-Aware Benchmark Reveals Memory Layout Matters for Graph-based ANNS on GPU","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2607.02266","title":"HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.23392","title":"Towards a Densing Law for User Representation Learning at Billion-Scale Capacity","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2610.03651","title":"MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}