6 papers
Test-Time Registers as Global Priors for Tokenized Image Generation
Cheng-Yao Hong, Yifan Wang, Yuewei Lin +1
Attention-based models often develop attention sinks, where a small number of tokens repeatedly attract attention and accumulate unusually large activations. In vision transformers…
Together, Then Apart: Balancing Alignment and Distinctiveness for Multimodal Survival Analysis
Wenjing Liu, Qin Ren, Wen Zhang +2
The paper introduces TTA, a framework that first aligns shared patterns across histopathology images and genomic data and then preserves modality‑specific information to improve ca…
GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agents
Xi Yu, Yang Yang, Qun Liu +3
Cellular image segmentation is essential for quantitative biology yet remains difficult due to heterogeneous modalities, morphological variability, and limited annotations. We pres…
Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference
Sk Miraj Ahmed, Xi Yu, Yunqi Li +2
Accurate biodiversity identification from large-scale field data is a foundational problem with direct impact on ecology, conservation, and environmental monitoring. In practice, t…
FCC: Fully Connected Correlation for One-Shot Segmentation
Seonghyeon Moon, Haein Kong, Muhammad Haris Khan +2
Few-shot segmentation (FSS) aims to segment the target object in a query image using only a small set of support images and masks. Therefore, having strong prior information for th…
Empirical Measurements of AI Training Power Demand on a GPU-Accelerated Node
Imran Latif, Alex C. Newkirk, Matthew R. Carbone +5
The expansion of artificial intelligence (AI) applications has driven substantial investment in computational infrastructure, especially by cloud computing providers. Quantifying t…