X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation
cs.CV, cs.LG, cs.SD
Submitted: 2026-10-09
Updated: 2026-10-09
Comments: Accepted at NeurIPS 2026. Camera-ready version forthcoming. 17 pages, 6 figures, 16 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MAEB: Massive Audio Embedding Benchmark
- Calibrated Dataset Condensation for Faster Hyperparameter Search
- DD-Ranking: Rethinking the Evaluation of Dataset Distillation
- The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Dataset Distillation
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models