14 citations · 21 across the 7 of their papers we have counts for
9 papers
Proper Scoring Rule-based Diffusion for Probabilistic Weather Forecasting
Joonhyeong Park, Giung Nam, Hyungi Lee +3
Recent probabilistic weather forecasters train stochastic predictors with the continuous ranked probability score (CRPS) to generate each ensemble member in a single forward pass.…
Efficient semantic uncertainty quantification in language models via diversity-steered sampling
Ji Won Park, Kyunghyun Cho
Accurately estimating semantic aleatoric and epistemic uncertainties in large language models (LLMs) is particularly challenging in free-form question answering (QA), where obtaini…
Supervised Contrastive Block Disentanglement
Taro Makino, Ji Won Park, Natasa Tagasovska +11
Real-world datasets often combine data collected under different experimental conditions. This yields larger datasets, but also introduces spurious correlations that make it diffic…
Concept Bottleneck Language Models For protein design
Aya Abdelsalam Ismail, Tuomas Oikarinen, Amy Wang +8
We introduce Concept Bottleneck Protein Language Models (CB-pLM), a generative masked language model with a layer where each neuron corresponds to an interpretable concept. Our arc…
Semiparametric conformal prediction
Ji Won Park, Robert Tibshirani, Kyunghyun Cho
Many risk-sensitive applications require well-calibrated prediction sets over multiple, potentially correlated target variables, for which the prediction algorithm may report corre…
Generalizing to any diverse distribution: uniformity, gentle finetuning and rebalancing
Andreas Loukas, Karolis Martinkus, Ed Wagstaff +1
As training datasets grow larger, we aspire to develop models that generalize well to any diverse test distribution, even if the latter deviates significantly from the training dat…
Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design
Nataša Tagasovska, Ji Won Park, Matthieu Kirchmeyer +8
Machine learning (ML) has demonstrated significant promise in accelerating drug design. Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model…
Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient
Nataša Tagasovska, Vladimir Gligorijević, Kyunghyun Cho +1
Across scientific domains, generating new models or optimizing existing ones while meeting specific criteria is crucial. Traditional machine learning frameworks for guided design u…
Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling
Romain Lopez, Nataša Tagasovska, Stephen Ra +3
Latent variable models such as the Variational Auto-Encoder (VAE) have become a go-to tool for analyzing biological data, especially in the field of single-cell genomics. One remai…