newsGoogle News — Machine LearningTrust 62 · AggregatorPublished yesterdayLive · yesterday
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization - Apple Machine Learning Research
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization Apple Machine Learning Research
Covers
paperA Self-Supervised Learning Framework for Video Encoding Complexity ClusteringpaperMLVC: Multi-platform Learned Video Codec for Real-World DeploymentpaperEnhanced Neural Video Representation Compression across Extreme Complexity and Quality ScalespaperLongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language ModelspaperDataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection
Covers (incoming)
Related across the graph
paperLongVQUBench: Benchmarking Long-Term Video Quality Understanding of Vision-Language ModelspaperWhen Token Compression Breaks: Structural Pruning vs. Token Reduction for Robust ViT Segmentation under High CompressionpaperMLVC: Multi-platform Learned Video Codec for Real-World DeploymentpaperA Self-Supervised Learning Framework for Video Encoding Complexity ClusteringpaperEnhanced Neural Video Representation Compression across Extreme Complexity and Quality ScalespaperDataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection