3 EMNLP 24 and NeurIPS 24 are accepted

From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment, EMNLP 2024 main,

with U Osaka and NVIDIA research

Bayesian Example Selection Improves In-Context Learning for Speech, Text, and Visual Modalities, EMNLP 2024 main

with THU

FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model, EMNLP 2024, industry track

with CMU

Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models, NeurIPS 2024 poster

with Nanyang Tech