CLIP with Quality Captions: A Strong Pretraining for Vision Tasks von Vasu, Pavan Kumar Anasosalu, Pouransari, Hadi, Faghri, Fartash, Tuzel, Oncel

Volltext bestellen

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training von Vasu, Pavan Kumar Anasosalu, Pouransari, Hadi, Faghri, Fartash, Vemulapalli, Raviteja, Tuzel, Oncel

Volltext bestellen

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum von Pouransari, Hadi, Li, Chun-Liang, Chang, Jen-Hao Rick, Vasu, Pavan Kumar Anasosalu, Koc, Cem, Shankar, Vaishaal, Tuzel, Oncel

Volltext bestellen

FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization von Vasu, Pavan Kumar Anasosalu, Gabriel, James, Zhu, Jeff, Tuzel, Oncel, Ranjan, Anurag

Volltext bestellen

Instance-Level Task Parameters: A Robust Multi-task Weighting Framework von Vasu, Pavan Kumar Anasosalu, Saxena, Shreyas, Tuzel, Oncel

Volltext bestellen

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding von Wang, Haoxiang, Vasu, Pavan Kumar Anasosalu, Faghri, Fartash, Vemulapalli, Raviteja, Farajtabar, Mehrdad, Mehta, Sachin, Rastegari, Mohammad, Tuzel, Oncel, Pouransari, Hadi

Volltext bestellen

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions von Hsieh, Yu-Guan, Hsieh, Cheng-Yu, Yeh, Shih-Ying, Béthune, Louis, Ansari, Hadi Pour, Vasu, Pavan Kumar Anasosalu, Li, Chun-Liang, Krishna, Ranjay, Tuzel, Oncel, Cuturi, Marco

Volltext bestellen

MobileOne: An Improved One millisecond Mobile Backbone von Vasu, Pavan Kumar Anasosalu, Gabriel, James, Zhu, Jeff, Tuzel, Oncel, Ranjan, Anurag

Volltext bestellen

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks von Pavan Kumar Anasosalu Vasu, Pouransari, Hadi, Faghri, Fartash, Oncel Tuzel

Volltext

Forward Compatible Training for Large-Scale Embedding Retrieval Systems von Ramanujan, Vivek, Vasu, Pavan Kumar Anasosalu, Farhadi, Ali, Tuzel, Oncel, Pouransari, Hadi

Volltext bestellen

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training von Pavan Kumar Anasosalu Vasu, Pouransari, Hadi, Faghri, Fartash, Vemulapalli, Raviteja, Oncel Tuzel

Volltext

Object detection with position, pose, and shape estimation von Saxena, Shreyas, Vasu, Pavan Kumar Anasosalu, Tuzel, Cuneyt Oncel

Volltext bestellen

FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization von Pavan Kumar Anasosalu Vasu, Gabriel, James, Zhu, Jeff, Oncel Tuzel, Ranjan, Anurag

Volltext

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding von Wang, Haoxiang, Pavan Kumar Anasosalu Vasu, Faghri, Fartash, Vemulapalli, Raviteja, Farajtabar, Mehrdad, Mehta, Sachin, Rastegari, Mohammad, Oncel Tuzel, Pouransari, Hadi

Volltext

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum von Pouransari, Hadi, Chun-Liang, Li, Jen-Hao, Rick Chang, Pavan Kumar Anasosalu Vasu, Koc, Cem, Shankar, Vaishaal, Oncel Tuzel

Volltext

MobileOne: An Improved One millisecond Mobile Backbone von Pavan Kumar Anasosalu Vasu, Gabriel, James, Zhu, Jeff, Oncel Tuzel, Ranjan, Anurag

Volltext

Instance-Level Task Parameters: A Robust Multi-task Weighting Framework von Pavan Kumar Anasosalu Vasu, Saxena, Shreyas, Oncel Tuzel

Volltext

Electronic Devices with Body Composition Analysis Circuitry von Anasosalu Vasu, Pavan Kumar, Keats, Liliana I, Sumanaweera, Thilaka S, Valsan, Gopal, Feathers, David J

Volltext bestellen

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions von Yu-Guan, Hsieh, Cheng-Yu, Hsieh, Shih-Ying Yeh, Béthune, Louis, Hadi Pour Ansari, Pavan Kumar Anasosalu Vasu, Chun-Liang, Li, Krishna, Ranjay, Oncel Tuzel, Cuturi, Marco

Volltext

Forward Compatible Training for Large-Scale Embedding Retrieval Systems von Ramanujan, Vivek, Pavan Kumar Anasosalu Vasu, Farhadi, Ali, Oncel Tuzel, Pouransari, Hadi

Volltext