10 papers
Evaluating Loss Functions in Differentiable Out-of-Domain Sound-Matching with Partial Parameter Distance
Amir Salimi, Daniel Penner, Kalvin Eng +2
In out-of-domain (OOD) sound-matching, a synthesizer is optimized to mimic a sound it did not generate. OOD evaluation of loss functions is underexplored in part because the standa…
Why Solve It Twice? Hierarchical Accumulation of Skills for Transfer-Efficient ML Engineering
Yongbin Kim, Yashar Talebirad, Osmar R. Zaiane
ML engineering agents waste compute rediscovering known techniques because every competition is a cold start. We present HASTE, a hierarchical multi-agent system that organizes cro…
From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agents
Yashar Talebirad, Eden Redman, Ali Parsaee +1
How do two agents invent a shared language from scratch? In a Lewis signaling game, a sender and receiver must coordinate on a code using only their interaction history. We study f…
BrainSCL: Subtype-Guided Contrastive Learning for Brain Disorder Diagnosis
Xiaolong Li, Guiliang Guo, Guangqi Wen +6
Mental disorder populations exhibit pronounced heterogeneity -- that is, the significant differences between samples -- poses a significant challenge to the definition of positive…
Learning the Hierarchical Organization in Brain Network for Brain Disorder Diagnosis
Jingfeng Tang, Peng Cao, Guangqi Wen +3
Brain network analysis based on functional Magnetic Resonance Imaging (fMRI) is pivotal for diagnosing brain disorders. Existing approaches typically rely on predefined functional…
SynMatch: Rethinking Consistency in Medical Image Segmentation with Sparse Annotations
Zhiqiang Shen, Peng Cao, Xiaoli Liu +2
Label scarcity remains a major challenge in deep learning-based medical image segmentation. Recent studies use strong-weak pseudo supervision to leverage unlabeled data. However, p…
ConStyX: Content Style Augmentation for Generalizable Medical Image Segmentation
Xi Chen, Zhiqiang Shen, Peng Cao +2
Medical images are usually collected from multiple domains, leading to domain shifts that impair the performance of medical image segmentation models. Domain Generalization (DG) ai…
Evaluating Sound Similarity Metrics for Differentiable, Iterative Sound-Matching
Amir Salimi, Abram Hindle, Osmar R. Zaiane
Manual sound design with a synthesizer is inherently iterative: an artist compares the synthesized output to a mental target, adjusts parameters, and repeats until satisfied. Itera…
Style Content Decomposition-based Data Augmentation for Domain Generalizable Medical Image Segmentation
Zhiqiang Shen, Peng Cao, Jinzhu Yang +2
Due to domain shifts across diverse medical imaging modalities, learned segmentation models often suffer significant performance degradation during deployment. We posit that these…
SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning
Chunzhen Jin, Yongfeng Huang, Yaqi Wang +2
Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources…