activity
20202026
most citedMixCo: Mix-up Contrastive Learning for Visual Representation

53 citations · 65 across the 16 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Youngrok Park, Sangmin Bae, Hojung Jung +6

Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This question is particularly important for successive model generati…

cs.LG2026

Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting

Soowon Oh, Nam Cao, Yujin Kim +4

Block-diffusion drafters have recently emerged as a powerful alternative for speculative decoding by predicting multiple future-token distributions in a single parallel step. Howev…

cs.LG2025

Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models

Youngrok Park, Hojung Jung, Sangmin Bae +1

Diffusion models have achieved remarkable success as generative models. However, even a well-trained model can accumulate errors throughout the generation process. These errors bec…

cs.LG2024

Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models

Yongjin Yang, Sihyeon Kim, Hojung Jung +4

Fine-tuning text-to-image diffusion models with human feedback is an effective method for aligning model behavior with human intentions. However, this alignment process often suffe…

cs.LG2024

Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers

Felix den Breejen, Sangmin Bae, Stephen Cha +1

The recently introduced TabPFN pretrains an In-Context Learning (ICL) transformer on synthetic data to perform tabular data classification. In this work, we extend TabPFN to the fi…

cs.LG20231 cited

Fine-Tuning the Retrieval Mechanism for Tabular Deep Learning

Felix den Breejen, Sangmin Bae, Stephen Cha +3

While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods. To narrow this performance gap, we explore…