← Search

Kanak Mahadik

2 accepted papers

2025

Fully Dynamic Embedding into $\ell_p$ Spaces

ICML 2025poster

Metric embeddings are fundamental in machine learning, enabling similarity search, dimensionality reduction, and representation learning. They underpin modern architectures like transformers and large language models, facilitating scalable training and improved generalization. Theoretically, the cla…

Cited by 0SourcePDFScholar
2024

ReCON: Training-Free Acceleration for Text-to-Image Synthesis with Retrieval of Concept Prompt Trajectories

ECCV 2024poster

"Text-to-image diffusion models excel in generating photo-realistic images but are hampered by slow processing times. Training-free retrieval-based acceleration methods, which leverage pre-generated “trajectories,” have been introduced to address this. Yet, these methods often lack diversity and fid…