OT-CAL: Optimal-Transport-Guided Adaptive Sample Selection for Efficient Visual Learning
cs.CV, cs.AI
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: 9 pages, 3 figures. Submitted to the IEEE BigData 2026 Workshop on Efficient AI
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Online Batch Selection for Faster Training of Neural Networks
- AdaSelection: Accelerating Deep Learning Training through Data Subsampling
- Practical Coreset Constructions for Machine Learning
- Accelerating Deep Learning by Focusing on the Biggest Losers
- On the Convergence of SGD with Biased Gradients
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs