Dyah Adila

7 papers · 2022–2025 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (20)

Venues

NeurIPS (3) ICLR (1) ICML (1) NAACL (1) UAI (1)

Top co-authors

Frederic Sala (6) Changho Shin (3) Sonia Cromp (2) Xintong Li (2) Tzu-Heng Huang (2) Nicholas Roberts (2) Daniel Y. Fu (1) Spencer Schoenberg (1) Linrong Cai (1) Michael Zhang (1)

Research topics

Machine Learning (7) Artificial Intelligence (6) Learning Types · Machine Learning (5) Core Methods (4) Deep Learning (3) Core AI (3) Learning Paradigms (3) Application Areas (2) Learning Types · Deep Learning (2) Natural Language Processing (1) Generation (1) Models (1)

Keywords

weak supervision (3) foundation model (2) transfer learning (2) zero-shot learning (2) domain adaptation (1) embedding space (1) model robustness (1) preference alignment (1) instruction tuning (1) frechet mean (1) bias mitigation (1) synthetic data (1) pre-trained model (1) latent space (1) metric space (1) representation editing (1) counterfactual fairness (1) labeling function (1) demographic parity (1) automated machine learning (1)

Papers

Personalize Your LLM: Fake it then Align it NAACL 2025 Discovering Bias in Latent Space: An Unsupervised Debiasing Approach ICML 2024 Zero-Shot Robustification of Zero-Shot Models ICLR 2024 Geometry-Aware Adaptation for Pretrained Models NeurIPS 2023 Mitigating Source Bias for Fairer Weak Supervision NeurIPS 2023 AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels NeurIPS 2022 Shoring up the foundations: fusing model embeddings and weak supervision UAI 2022