6 citations · 6 across the 4 of their papers we have counts for
4 papers
Variable-Length Tokenization via Learnable Global Merging for Diffusion Transformers
Dong Hoon Lee, Seunghoon Hong
Latent Diffusion Models (LDMs) have become dominant in visual synthesis, but their quality-compute trade-off is largely constrained by the tokenizer's fixed compression ratio. Vari…
Disentangled Representation Learning via Modular Compositional Bias
Whie Jung, Dong Hoon Lee, Seunghoon Hong
Recent disentangled representation learning (DRL) methods heavily rely on factor specific strategies-either learning objectives for attributes or model architectures for objects-to…
Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
Dong Hoon Lee, Seunghoon Hong
Recent token reduction methods for Vision Transformers (ViTs) incorporate token merging, which measures the similarities between token embeddings and combines the most similar pair…
Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
Dong Hoon Lee, Sae-Young Chung
We propose unsupervised embedding adaptation for the downstream few-shot classification task. Based on findings that deep neural networks learn to generalize before memorizing, we…