Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models
Uncertainty-aware knowledge distillation that adaptively balances data supervision and teacher guidance.
jingchen-sun
Uncertainty-aware knowledge distillation that adaptively balances data supervision and teacher guidance.
Real-world deployment requires sound event and acoustic scene classification systems to remain reliable in noisy, diverse environments on resource-constrained devices. Although …
Reparameterization and randomized parameter sharing for extreme parameter-efficient fine-tuning.
Distributed fiber-optic sensing combined with machine learning enables continuous monitoring of telecom infrastructure. We employ generative modeling for event classification, …
Combines support-set exemplar memory with parametric adaptation for pretrained audio-language models under severe domain shifts.
Vector-bank parameter sharing for extreme parameter-efficient fine-tuning.
This paper studies zero-shot domain adaptation where each domain is indexed on a multi-dimensional array, and we only have data from a small subset of domains. Our goal is to …
Transferable reward learning with test-time policy adaptation to unseen target classes.
Variational inference for flexible dependence modeling with Gaussian copulas.
We propose a semi-parametric and dynamic rank factor model for topic modeling, capable of (i) discovering topic prevalence over time, and (ii) learning contemporary multi-scale …