Alert button
Picture for Karttikeya Mangalam

Karttikeya Mangalam

Alert button

Do Vision and Language Encoders Represent the World Similarly?

Jan 10, 2024
Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Mohamed El Amine Seddik, Karttikeya Mangalam, Noel E. O'Connor

Viaarxiv icon

Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning

Jan 08, 2024
Chen Zhao, Shuming Liu, Karttikeya Mangalam, Guocheng Qian, Fatimah Zohra, Abdulmohsen Alghannam, Jitendra Malik, Bernard Ghanem

Viaarxiv icon

Adaptive Human Trajectory Prediction via Latent Corridors

Dec 11, 2023
Neerja Thakkar, Karttikeya Mangalam, Andrea Bajcsy, Jitendra Malik

Figure 1 for Adaptive Human Trajectory Prediction via Latent Corridors
Figure 2 for Adaptive Human Trajectory Prediction via Latent Corridors
Figure 3 for Adaptive Human Trajectory Prediction via Latent Corridors
Figure 4 for Adaptive Human Trajectory Prediction via Latent Corridors
Viaarxiv icon

Sequential Modeling Enables Scalable Learning for Large Vision Models

Dec 01, 2023
Yutong Bai, Xinyang Geng, Karttikeya Mangalam, Amir Bar, Alan Yuille, Trevor Darrell, Jitendra Malik, Alexei A Efros

Viaarxiv icon

EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding

Aug 17, 2023
Karttikeya Mangalam, Raiymbek Akshulakov, Jitendra Malik

Viaarxiv icon

PaReprop: Fast Parallelized Reversible Backpropagation

Jun 15, 2023
Tyler Zhu, Karttikeya Mangalam

Figure 1 for PaReprop: Fast Parallelized Reversible Backpropagation
Figure 2 for PaReprop: Fast Parallelized Reversible Backpropagation
Figure 3 for PaReprop: Fast Parallelized Reversible Backpropagation
Figure 4 for PaReprop: Fast Parallelized Reversible Backpropagation
Viaarxiv icon

Diffusion Models as Masked Autoencoders

Apr 06, 2023
Chen Wei, Karttikeya Mangalam, Po-Yao Huang, Yanghao Li, Haoqi Fan, Hu Xu, Huiyu Wang, Cihang Xie, Alan Yuille, Christoph Feichtenhofer

Figure 1 for Diffusion Models as Masked Autoencoders
Figure 2 for Diffusion Models as Masked Autoencoders
Figure 3 for Diffusion Models as Masked Autoencoders
Figure 4 for Diffusion Models as Masked Autoencoders
Viaarxiv icon

Big Little Transformer Decoder

Feb 15, 2023
Sehoon Kim, Karttikeya Mangalam, Jitendra Malik, Michael W. Mahoney, Amir Gholami, Kurt Keutzer

Figure 1 for Big Little Transformer Decoder
Figure 2 for Big Little Transformer Decoder
Figure 3 for Big Little Transformer Decoder
Figure 4 for Big Little Transformer Decoder
Viaarxiv icon

Reversible Vision Transformers

Feb 09, 2023
Karttikeya Mangalam, Haoqi Fan, Yanghao Li, Chao-Yuan Wu, Bo Xiong, Christoph Feichtenhofer, Jitendra Malik

Figure 1 for Reversible Vision Transformers
Figure 2 for Reversible Vision Transformers
Figure 3 for Reversible Vision Transformers
Figure 4 for Reversible Vision Transformers
Viaarxiv icon

Does unsupervised grammar induction need pixels?

Dec 20, 2022
Boyi Li, Rodolfo Corona, Karttikeya Mangalam, Catherine Chen, Daniel Flaherty, Serge Belongie, Kilian Q. Weinberger, Jitendra Malik, Trevor Darrell, Dan Klein

Figure 1 for Does unsupervised grammar induction need pixels?
Figure 2 for Does unsupervised grammar induction need pixels?
Figure 3 for Does unsupervised grammar induction need pixels?
Figure 4 for Does unsupervised grammar induction need pixels?
Viaarxiv icon