6 papers
Training Text-to-Molecule Models with Context-Aware Tokenization
Seojin Kim, Hyeontae Song, Jaehyun Nam +1
Recently, text-to-molecule models have shown great potential across various chemical applications, e.g., drug-discovery. These models adapt language models to molecular data by rep…
FontAdapter: Instant Font Adaptation in Visual Text Generation
Myungkyu Koo, Subin Kim, Sangkyung Kwak +3
Text-to-image diffusion models have significantly improved the seamless integration of visual text into diverse image contexts. Recent approaches further improve control over font…
Mamba Drafters for Speculative Decoding
Daewon Choi, Seunghyuk Oh, Saket Dingliwal +9
Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target mode…
Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
Suhyeok Jang, Seojin Kim, Jinwoo Shin +1
The remarkable advances in deep learning have led to the emergence of many off-the-shelf classifiers, e.g., large pre-trained models. However, since they are typically trained on c…
Data-Efficient Molecular Generation with Hierarchical Textual Inversion
Seojin Kim, Jaehyun Nam, Sihyun Yu +2
Developing an effective molecular generation framework even with a limited number of molecules is often important for its practical deployment, e.g., drug discovery, since acquirin…
Confidence-aware Training of Smoothed Classifiers for Certified Robustness
Jongheon Jeong, Seojin Kim, Jinwoo Shin
Any classifier can be "smoothed out" under Gaussian noise to build a new classifier that is provably robust to -adversarial perturbations, viz., by averaging its prediction…