Yuki M. Asano
Graph View
Backlinks
- Elastic ViTs from Pretrained Models without Retraining
- Franca - Nested Matryoshka Clustering for Scalable Visual Representation Learning
- Is ImageNet worth 1 video Learning strong image encoders from 1 long unlabelled video
- KV Cache Steering for Inducing Reasoning in Small Language Models
- Lost in Time - A New Temporal Benchmark for VideoLLMs
- MoSiC - Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning
- Near, far - Patch-ordering enhances vision foundation models' scene understanding
- No Train, all Gain - Self-Supervised Gradients Improve Deep Frozen Representations Yuki M Asano
- PIN - Positional Insert Unlocks Object Localisation Abilities in VLMs
- Self-Guided Diffusion Models
- Self-Supervised Learning of Object Parts for Semantic Segmentation
- Self-Supervised Learning of Structured Dynamics from Videos
- Steerable Visual Representations