{"total":14,"rows":[{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69,"area":null},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52,"area":null},{"id":"2203.13751","title":"Efficient-VDVAE: Less is more","created":"2022-03-25","cited_by_count":26,"area":null},{"id":"2204.08058","title":"MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration","created":"2022-04-17","cited_by_count":20,"area":null},{"id":"2207.11240","title":"Discrete Key-Value Bottleneck","created":"2022-07-22","cited_by_count":18,"area":null},{"id":"2208.10922","title":"StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation","created":"2022-08-23","cited_by_count":14,"area":null},{"id":"2504.06084","title":"MAPLE: Encoding Dexterous Robotic Manipulation Priors Learned From Egocentric Videos","created":"2025-04-08","cited_by_count":12,"area":null},{"id":"2411.16550","title":"Representation Collapsing Problems in Vector Quantization","created":"2024-11-25","cited_by_count":10,"area":null},{"id":"2603.00632","title":"Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale","created":"2026-02-28","cited_by_count":6,"area":null},{"id":"2312.03406","title":"Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach","created":"2023-12-06","cited_by_count":3,"area":null},{"id":"2609.31862","title":"Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Tasks","created":"2026-09-25","cited_by_count":2,"area":null},{"id":"2212.11296","title":"Towards Neural Variational Monte Carlo That Scales Linearly with System Size","created":"2022-12-21","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":"2503.04940","title":"VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization","created":"2025-03-06","cited_by_count":0,"area":null}],"next_cursor":null}