collaborators

7 papers

cs.CV2025

Merlin L48 Spectrogram Dataset

Aaron Sun, Subhransu Maji, Grant Van Horn

In the single-positive multi-label (SPML) setting, each image in a dataset is labeled with the presence of a single class, while the true presence of other classes remains unknown.…

cs.CV2025

You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction

Logan Lawrence, Oindrila Saha, Megan Wei +3

Despite the renewed interest in zero-shot visual classification due to the rise of Multimodal Large Language Models (MLLMs), the problem of evaluating free-form responses of auto-r…

cs.LG2025

Consensus-Driven Active Model Selection

Justin Kay, Grant Van Horn, Subhransu Maji +2

The widespread availability of off-the-shelf machine learning models poses a challenge: which model, of the many available candidates, should be chosen for a given data analysis ta…

cs.CV2025

Moment Sampling in Video LLMs for Long-Form Video QA

Mustafa Chasmai, Gauri Jagatap, Gouthaman KV +3

Recent advancements in video large language models (Video LLMs) have significantly advanced the field of video question answering (VideoQA). While existing methods perform well on…

cs.CV2025

Feedforward Few-shot Species Range Estimation

Christian Lange, Max Hamilton, Elijah Cole +6

Knowing where a particular species can or cannot be found on Earth is crucial for ecological research and conservation efforts. By mapping the spatial ranges of all species, we wou…

cs.CV2025

Generate, Transduct, Adapt: Iterative Transduction with VLMs

Oindrila Saha, Logan Lawrence, Grant Van Horn +1

Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductiv…