|
Workshop
|
Sat 11:00
|
Optimizing Data Use for Efficient Pre-training
Danqi Chen
|
|
|
Workshop
|
|
Distributionally robust self-supervised learning for tabular data
Shantanu Ghosh · Tiankang Xie · Mikhail Kuznetsov
|
|
|
Workshop
|
|
Data-Efficient Training by Evolved Sampling
Ziheng Cheng · Zhong Li · Jiang Bian
|
|
|
Poster
|
|
Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
Andrea Schioppa
|
|
|
Tutorial
|
Tue 9:30
|
Opening the Language Model Pipeline: A Tutorial on Data Preparation, Model Training, and Adaptation
Kyle Lo · Akshita Bhagia · Nathan Lambert
|
|
|
Poster
|
Wed 16:30
|
Training Data Attribution via Approximate Unrolling
Juhan Bae · Wu Lin · Jonathan Lorraine · Roger Grosse
|
|
|
Workshop
|
|
Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data
Spencer Whitehead · Jacob Phillips · Sean Hendryx
|
|
|
Workshop
|
|
Investigating LLM Memorization: Bridging Trojan Detection and Training Data Extraction
Manoj Acharya · Xiao Lin · Susmit Jha
|
|
|
Poster
|
|
Can We Leave Deepfake Data Behind in Training Deepfake Detector?
Jikang Cheng · Zhiyuan Yan · Ying Zhang · Yuhao Luo · Zhongyuan Wang · Chen Li
|
|
|
Workshop
|
|
Network Inversion for Training-Like Data Reconstruction
Pirzada Suhail · Amit Sethi
|
|
|
Poster
|
Thu 16:30
|
Pre-training Differentially Private Models with Limited Public Data
Zhiqi Bu · Xinwei Zhang · Sheng Zha · Mingyi Hong · George Karypis
|
|
|
Workshop
|
|
The Association Between Training Data and Text-to-Image Generation Capabilities
Preethi Seshadri · Yasaman Razeghi · Sameer Singh · Yanai Elazar
|
|
