|
Poster
|
Thu 16:30
|
Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
Hanyang Yuan · Jiarong Xu · Renhong Huang · Mingli Song · Chunping Wang · YANG YANG
|
|
|
Workshop
|
|
Understanding Critical Batch Sizes: Scheduling and Batch-Size Invariance in Data-constrained Pre-training
Hanlin Zhang · Depen Morwani · Nikhil Vyas · Jingfeng Wu · Difan Zou · Udaya Ghai · Dean Foster · Sham Kakade
|
|
|
Workshop
|
|
Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
Binghui Li · Yuanzhi Li
|
|
|
Workshop
|
|
CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
Joshua Kazdan · Hao Sun · Jiaqi Han · Felix Petersen · Frederick Vu · Stefano Ermon
|
|
|
Poster
|
Thu 16:30
|
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
Scott Geng · Cheng-Yu Hsieh · Vivek Ramanujan · Matthew Wallingford · Chun-Liang Li · Pang Wei Koh · Ranjay Krishna
|
|
|
Poster
|
Fri 11:00
|
Changing the Training Data Distribution to Reduce Simplicity Bias Improves In-distribution Generalization
Dang Nguyen · Paymon Haddad · Eric Gan · Baharan Mirzasoleiman
|
|
|
Workshop
|
|
Synthetic Multimodal Data Generation and Training Optimization For Computed Tomography Cardiac Imaging Applications
Masaki Ikuta · Quanqi Hu · Ashok Addala · Ravi Soni · Avinash Gopal
|
|
|
Workshop
|
|
Measuring Pre-training Data Quality without Labels for Time Series Foundation Models
Songkang Wen · Vasilii Feofanov · Jianfeng Zhang
|
|
|
Workshop
|
|
Sometimes I am a Tree: Data Drives Fragile Hierarchical Generalization
Tian Qin · Naomi Saphra · David Alvarez-Melis
|
|
|
Workshop
|
|
Leveraging Pre-Trained LMs for Rapid and Accurate Structure Elucidation from 2D NMR Data
Susanna Di Vita · Florian Grötschla · Luca Lanzendörfer · Roger Wattenhofer
|
|
|
Poster
|
Thu 16:30
|
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
Omead Pooladzandi · Sunay Bhat · Jeffrey Jiang · Alexander Branch · Gregory Pottie
|
|
|
Poster
|
Fri 16:30
|
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
Johannes Treutlein · Dami Choi · Jan Betley · Samuel Marks · Cem Anil · Roger Grosse · Owain Evans
|
|
