5 papers
Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators
Tongtong Fang, Nan Lu, Gang Niu +2
Importance weighting (IW) is a golden solver for joint distribution shift, where the joint distributions differ between the training and test data. To solve this problem, IW estima…
Corruptions of Supervised Learning Problems: Typology and Mitigations
Laura Iacovissi, Nan Lu, Robert C. Williamson
Corruption is notoriously widespread in data collection. Despite extensive research, the existing literature predominantly focuses on specific settings and learning scenarios, lack…
TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis
Qifan Liang, Yuansen Liu, Ruixin Wei +3
While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance ex…
Contextual Online Uncertainty-Aware Preference Learning for Human Feedback
Nan Lu, Ethan Lee, Ethan X. Fang +1
Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human preferences. In this paper, we propose a…
Learning from Ambiguous Data with Hard Labels
Zeke Xie, Zheng He, Nan Lu +5
Real-world data often contains intrinsic ambiguity that the common single-hard-label annotation paradigm ignores. Standard training using ambiguous data with these hard labels may…