Skyler Seto

Closing the Gap Between Text and Speech Understanding in LLMs

Normalized Rewards for Preference Learning

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging