Skip to yearly menu bar Skip to main content


(10 events)   Timezone:  
Show all
Toggle Poster Visibility
Oral
Thu Jul 27 06:00 PM -- 06:08 PM (PDT) @ Ballroom A None
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
In Oral C3 Multimodal and Pretaining
Kenton Lee · Mandar Joshi · Iulia Turc · Hexiang Hu · Fangyu Liu · Julian M Eisenschlos · Urvashi Khandelwal · Peter Shaw · Ming-Wei Chang · Kristina Toutanova
[ PDF] 
Oral
Thu Jul 27 06:08 PM -- 06:16 PM (PDT) @ Ballroom A None
Calibrating Multimodal Learning
In Oral C3 Multimodal and Pretaining
Huan Ma · Qingyang Zhang · Changqing Zhang · Bingzhe Wu · Huazhu Fu · Joey Tianyi Zhou · Qinghua Hu
[ PDF] 
Oral
Thu Jul 27 06:16 PM -- 06:24 PM (PDT) @ Ballroom A None
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
In Oral C3 Multimodal and Pretaining
Axel Sauer · Tero Karras · Samuli Laine · Andreas Geiger · Timo Aila
[ PDF] 
Oral
Thu Jul 27 06:24 PM -- 06:32 PM (PDT) @ Ballroom A None
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
In Oral C3 Multimodal and Pretaining
Minghao Xu · Xinyu Yuan · Santiago Miret · Jian Tang
[ PDF] 
Oral
Thu Jul 27 06:32 PM -- 06:40 PM (PDT) @ Ballroom A None
Cross-Modal Fine-Tuning: Align then Refine
In Oral C3 Multimodal and Pretaining
Junhong Shen · Liam Li · Lucio Dery · Corey Staten · Mikhail Khodak · Graham Neubig · Ameet Talwalkar
[ PDF] 
Oral
Thu Jul 27 06:40 PM -- 06:48 PM (PDT) @ Ballroom A None
Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models
In Oral C3 Multimodal and Pretaining
Yong Cheng · Yu Zhang · Melvin Johnson · Wolfgang Macherey · Ankur Bapna
[ PDF] 
Oral
Thu Jul 27 06:48 PM -- 06:56 PM (PDT) @ Ballroom A None
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
In Oral C3 Multimodal and Pretaining
Zichang Liu · Jue Wang · Tri Dao · Tianyi Zhou · Binhang Yuan · Zhao Song · Anshumali Shrivastava · Ce Zhang · Yuandong Tian · Christopher Re · Beidi Chen
[ PDF] 
Oral
Thu Jul 27 06:56 PM -- 07:04 PM (PDT) @ Ballroom A None
Pre-training for Speech Translation: CTC Meets Optimal Transport
In Oral C3 Multimodal and Pretaining
Phuong-Hang Le · Hongyu Gong · Changhan Wang · Juan Pino · Benjamin Lecouteux · Didier Schwab
[ Slides]  [ PDF] 
Oral
Thu Jul 27 07:04 PM -- 07:12 PM (PDT) @ Ballroom A None
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models
In Oral C3 Multimodal and Pretaining
Hong Liu · Sang Michael Xie · Zhiyuan Li · Tengyu Ma
[ PDF] 
Oral
Thu Jul 27 07:12 PM -- 07:20 PM (PDT) @ Ballroom A None
Spherical Inducing Features for Orthogonally-Decoupled Gaussian Processes
In Oral C3 Multimodal and Pretaining
Louis Chi-Chun Tiao · Vincent Dutordoir · Victor Picheny
[ PDF]