Publications (12)
Does CLIP Bind Concepts? Probing Compositionality in Large Image Models
Martha Lewis, Nihal V. Nayak, Peilin Yu +4
Large-scale neural network models combining text and images have made incredible progress in recent years. However, it remains an open question to what extent such models encode co…
Stability Annealing Selects the Implicit Bias of Smoothed Sign Descent: A Rate-Indexed Barrier Path on Separable Data
Xiangwu Wang, Chengwei Cao, Yicheng Song +2
Adaptive gradient methods can favor max-margin separators that differ from gradient descent, yet a fixed positive numerical stability constant eventually changes the update geometr…
Large-Scale Riemannian Meta-Optimization via Subspace Adaptation
Peilin Yu, Yuwei Wu, Zhi Gao +2
Riemannian meta-optimization provides a promising approach to solving non-linear constrained optimization problems, which trains neural networks as optimizers to perform optimizati…
Alfred: A System for Prompted Weak Supervision
Peilin Yu, Stephen H. Bach
Alfred is the first system for programmatic weak supervision (PWS) that creates training data for machine learning by prompting. In contrast to typical PWS systems where weak super…
Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
Nihal V. Nayak, Peilin Yu, Stephen H. Bach
We introduce compositional soft prompting (CSP), a parameter-efficient learning technique to improve the zero-shot compositionality of large-scale pretrained vision-language models…
VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
Simon Yu, Peilin Yu, Hongbo Zheng +3
We present VISAT, a novel open dataset and benchmarking suite for evaluating model robustness in the task of traffic sign recognition with the presence of visual attributes. Built…
A Set-to-Set Distance Measure in Hyperbolic Space
Pengxiang Li, Wei Wu, Zhi Gao +6
We propose a hyperbolic set-to-set distance measure for computing dissimilarity between sets in hyperbolic space. While point-to-point distances in hyperbolic space effectively cap…
Learning from Multiple Noisy Partial Labelers
Peilin Yu, Tiffany Ding, Stephen H. Bach
Programmatic weak supervision creates models without hand-labeled training data by combining the outputs of heuristic labelers. Existing frameworks make the restrictive assumption…
DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction
Shun Zheng, Xu Han, Yankai Lin +5
Pattern-based labeling methods have achieved promising results in alleviating the inevitable labeling noises of distantly supervised neural relation extraction. However, these meth…
A Scale-adaptive Vision Model Links C. elegans Neuronal Morphology to Behavior for Neurotoxicity Assessment
Haochao Ying, Shenchong Lv, Yutao Sun +8
Neurological disorders are a leading cause of global disability and are increasingly linked to environmental chemical exposures. Yet neurotoxicity assessment still relies on hand-s…
Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision
Jinyan Su, Peilin Yu, Jieyu Zhang +1
Prompted weak supervision (PromptedWS) applies pre-trained large language models (LLMs) as the basis for labeling functions (LFs) in a weak supervision framework to obtain large la…
Hyperbolic Dual Feature Augmentation for Open-Environment
Peilin Yu, Yuwei Wu, Zhi Gao +3
Feature augmentation generates novel samples in the feature space, providing an effective way to enhance the generalization ability of learning algorithms with hyperbolic geometry.…