Bryan A. Plummer

Assistant Professor@Boston University·美国·OpenReview

研究方向

Learning with noisy labels · Bias Mitigation · Image editing · Domain Adaptation and Generalization · Efficient Deep Learning · Misinformation detection · XAI · AI for Fashion · Vision and language

Bryan A. Plummer

Right Side Up? Disentangling Orientation Understanding in MLLMs with Fine-grained Multi-axis Perception Tasks

CHAMMI-75: Pre-training multi-channel models with heterogeneous microscopy images

Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalization

Fine-grained Token Allocation Via Operation Pruning for Efficient MLLMs

OP-LoRA: The Blessing of Dimensionality with Overparameterized Low-Rank Adaptation

SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models

ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning

Is Large-scale Pretraining the Secret to Good Domain Generalization?

RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks

Multi-domain Analysis and Generalization of Image manipulation loCalization

Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling

Fine-Grained Machine-Generated Text Detection

In-N-Out: Robustness to In-Domain Noise and Out-of-Domain Generalization

Hidden Logos in Web-Scale Data Disrupt Large Vision Language Models