firstbacksecondback
65 Results
|
Workshop
|
Small-to-Large Generalization: Training Data Influences Models Consistently Across Scale Alaa Khaddaj · Logan Engstrom · Aleksander Madry |
||
|
Poster
|
Wed 16:30 |
Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data Rui Huang · Henry Zheng · Yan Wang · Zhuofan Xia · Marco Pavone · Gao Huang |
|
|
Poster
|
Fri 11:00 |
On the Ability of Developers' Training Data Preservation of Learnware Hao-Yi Lei · Zhi-Hao Tan · Zhi-Hua Zhou |
|
|
Workshop
|
Efficient Ensembles Improve Training Data Attribution Junwei Deng · Ting-Wei Li · Shichang (Ray) Zhang · Jiaqi Ma |
||
|
Workshop
|
TurboMoE: Enhancing MoE Model Training with Smart Kernel-Fusion and Data Transformation Reza Yazdani Aminabadi · Connor Holmes · Samyam Rajbhandari · Zhewei Yao · Yuxiong He |
||
|
Poster
|
Thu 11:00 |
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers Chandramouli Shama Sastry · Sri Harsha Dumpala · Sageev Oore |
|
|
Workshop
|
Sat 13:45 |
BLAP: Bootstrapping Language-Audio Pre-training for Music Captioning Luca Lanzendörfer · Constantin Pinkl · Nathanael Perraudin · Roger Wattenhofer |
|
|
Poster
|
Thu 16:30 |
Extracting Training Data from Molecular Pre-trained Models Renhong Huang · Jiarong Xu · Zhiming Yang · Xiang Si · Xin Jiang · Hanyang Yuan · Chunping Wang · YANG YANG |
|
|
Workshop
|
Flood Prediction in Kenya - Leveraging Pre-Trained Models to Generate More Validation Data in a Sparse Observation Settings Alim Karimi · David Quispe · Hammed Akande · Nicole Mongare · Valerie Brosnan · Asbina Baral |
||
|
Poster
|
Thu 16:30 |
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions Jonathan Hayase · Alisa Liu · Yejin Choi · Sewoong Oh · Noah Smith |
|
|
Poster
|
Wed 11:00 |
What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights Xin Wen · Bingchen Zhao · Yilun Chen · Jiangmiao Pang · Xiaojuan Qi |
|
|
Poster
|
Fri 11:00 |
G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training Che Liu · Cheng Ouyang · Sibo Cheng · Anand Shah · Wenjia Bai · Rossella Arcucci |