Karttikeya Mangalam

63 papers A* 20A 4Journal 33Unranked 5
YearRankTypeTitle / Venue / Authors
2025 J jnl
Ego4D: Around the World in 3,600 Hours of Egocentric Video.
IEEE Trans. Pattern Anal. Mach. Intell.
Kristen Grauman, Andrew Westbury, Eugene Byrne, Vincent Cartillier, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Devansh Kukreja, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Abrham Gebreselasie, Cristina González, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jáchym Kolár, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran K. Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Ziwei Zhao, Yunyi Zhu, Pablo Arbeláez, David Crandall, Dima Damen, Giovanni Maria Farinella, Christian Fuegen, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard A. Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik
2025 A conf
Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization.
EuroSys
Zhanda Zhu, Christina Giannoula, Muralidhar Andoorveedu, Qidong Su, Karttikeya Mangalam, Bojian Zheng, Gennady Pekhimenko
2025 J jnl
Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization.
CoRR
Zhanda Zhu, Christina Giannoula, Muralidhar Andoorveedu, Qidong Su, Karttikeya Mangalam, Bojian Zheng, Gennady Pekhimenko
2024 — conf
Adaptive Human Trajectory Prediction via Latent Corridors.
ECCV (38)
Neerja Thakkar, Karttikeya Mangalam, Andrea Bajcsy, Jitendra Malik
2024 A* conf
Do Vision and Language Encoders Represent the World Similarly?
CVPR
Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali, Mohamed El Amine Seddik, Sanath Narayan, Karttikeya Mangalam, Noel E. O'Connor
2024 J jnl
Do Vision and Language Encoders Represent the World Similarly?
CoRR
Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Mohamed El Amine Seddik, Karttikeya Mangalam, Noel E. O'Connor
2024 A* conf
Dr
CVPR
Chen Zhao, Shuming Liu, Karttikeya Mangalam, Guocheng Qian, Fatimah Zohra, Abdulmohsen Alghannam, Jitendra Malik, Bernard Ghanem
2024 J jnl
Dr
CoRR
Chen Zhao, Shuming Liu, Karttikeya Mangalam, Guocheng Qian, Fatimah Zohra, Abdulmohsen Alghannam, Jitendra Malik, Bernard Ghanem
2024 — conf
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement.
ACL (Findings)
Nicholas Lee, Thanakul Wattanawong, Sehoon Kim, Karttikeya Mangalam, Sheng Shen, Gopala Anumanchipalli, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2024 J jnl
LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement.
CoRR
Nicholas Lee, Thanakul Wattanawong, Sehoon Kim, Karttikeya Mangalam, Sheng Shen, Gopala Anumanchipalli, Michael W. Mahoney, Kurt Keutzer, Amir Gholami
2024 — conf
Re-evaluating the Need for Visual Signals in Unsupervised Grammar Induction.
NAACL-HLT (Findings)
Boyi Li, Rodolfo Corona, Karttikeya Mangalam, Catherine Chen, Daniel Flaherty, Serge J. Belongie, Kilian Q. Weinberger, Jitendra Malik, Trevor Darrell, Dan Klein
2024 A* conf
Sequential Modeling Enables Scalable Learning for Large Vision Models.
CVPR
Yutong Bai, Xinyang Geng, Karttikeya Mangalam, Amir Bar, Alan L. Yuille, Trevor Darrell, Jitendra Malik, Alexei A. Efros
2024 A* conf
xT: Nested Tokenization for Larger Context in Large Images.
ICML
Ritwik Gupta, Shufan Li, Tyler Zhu, Jitendra Malik, Trevor Darrell, Karttikeya Mangalam
2024 J jnl
xT: Nested Tokenization for Larger Context in Large Images.
CoRR
Ritwik Gupta, Shufan Li, Tyler Zhu, Jitendra Malik, Trevor Darrell, Karttikeya Mangalam
2023 J jnl
Adaptive Human Trajectory Prediction via Latent Corridors.
CoRR
Neerja Thakkar, Karttikeya Mangalam, Andrea Bajcsy, Jitendra Malik
2023 J jnl
Big Little Transformer Decoder.
CoRR
Sehoon Kim, Karttikeya Mangalam, Jitendra Malik, Michael W. Mahoney, Amir Gholami, Kurt Keutzer
2023 A* conf
Diffusion Models as Masked Autoencoders.
ICCV
Chen Wei, Karttikeya Mangalam, Po-Yao Huang, Yanghao Li, Haoqi Fan, Hu Xu, Huiyu Wang, Cihang Xie, Alan L. Yuille, Christoph Feichtenhofer
2023 J jnl
Diffusion Models as Masked Autoencoders.
CoRR
Chen Wei, Karttikeya Mangalam, Po-Yao Huang, Yanghao Li, Haoqi Fan, Hu Xu, Huiyu Wang, Cihang Xie, Alan L. Yuille, Christoph Feichtenhofer
2023 A* conf
EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding.
NeurIPS
Karttikeya Mangalam, Raiymbek Akshulakov, Jitendra Malik
2023 J jnl
EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding.
CoRR
Karttikeya Mangalam, Raiymbek Akshulakov, Jitendra Malik
2023 A* conf
Latency Matters: Real-Time Action Forecasting Transformer.
CVPR
Harshayu Girase, Nakul Agarwal, Chiho Choi, Karttikeya Mangalam
2023 J jnl
PaReprop: Fast Parallelized Reversible Backpropagation.
CoRR
Tyler Zhu, Karttikeya Mangalam
2023 — —
Perceiving People over Long Periods: Algorithms, Architectures & Datasets
Karttikeya Mangalam
2023 A* conf
Re
CVPR
Chen Zhao, Shuming Liu, Karttikeya Mangalam, Bernard Ghanem
2023 J jnl
Reversible Vision Transformers.
CoRR
Karttikeya Mangalam, Haoqi Fan, Yanghao Li, Chao-Yuan Wu, Bo Xiong, Christoph Feichtenhofer, Jitendra Malik
2023 J jnl
Sequential Modeling Enables Scalable Learning for Large Vision Models.
CoRR
Yutong Bai, Xinyang Geng, Karttikeya Mangalam, Amir Bar, Alan L. Yuille, Trevor Darrell, Jitendra Malik, Alexei A. Efros
2023 A* conf
Speculative Decoding with Big Little Decoder.
NeurIPS
Sehoon Kim, Karttikeya Mangalam, Suhong Moon, Jitendra Malik, Michael W. Mahoney, Amir Gholami, Kurt Keutzer
2022 A* conf
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens.
NeurIPS
Elad Ben-Avraham, Roei Herzig, Karttikeya Mangalam, Amir Bar, Anna Rohrbach, Leonid Karlinsky, Trevor Darrell, Amir Globerson
2022 J jnl
Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens.
CoRR
Elad Ben-Avraham, Roei Herzig, Karttikeya Mangalam, Amir Bar, Anna Rohrbach, Leonid Karlinsky, Trevor Darrell, Amir Globerson
2022 J jnl
Does unsupervised grammar induction need pixels?
CoRR
Boyi Li, Rodolfo Corona, Karttikeya Mangalam, Catherine Chen, Daniel Flaherty, Serge J. Belongie, Kilian Q. Weinberger, Jitendra Malik, Trevor Darrell, Dan Klein
2022 A* conf
Ego4D: Around the World in 3, 000 Hours of Egocentric Video.
CVPR
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Abrham Gebreselasie, Cristina González, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jáchym Kolár, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran K. Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Ziwei Zhao, Yunyi Zhu, Pablo Arbeláez, David Crandall, Dima Damen, Giovanni Maria Farinella, Christian Fuegen, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard A. Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik
2022 A* conf
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection.
CVPR
Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, Christoph Feichtenhofer
2022 A* conf
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition.
CVPR
Chao-Yuan Wu, Yanghao Li, Karttikeya Mangalam, Haoqi Fan, Bo Xiong, Jitendra Malik, Christoph Feichtenhofer
2022 J jnl
MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition.
CoRR
Chao-Yuan Wu, Yanghao Li, Karttikeya Mangalam, Haoqi Fan, Bo Xiong, Jitendra Malik, Christoph Feichtenhofer
2022 A* conf
Object-Region Video Transformers.
CVPR
Roei Herzig, Elad Ben-Avraham, Karttikeya Mangalam, Amir Bar, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson
2022 J jnl
Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization.
CoRR
Chen Zhao, Shuming Liu, Karttikeya Mangalam, Bernard Ghanem
2022 A* conf
Reversible Vision Transformers.
CVPR
Karttikeya Mangalam, Haoqi Fan, Yanghao Li, Chao-Yuan Wu, Bo Xiong, Christoph Feichtenhofer, Jitendra Malik
2022 A* conf
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition.
NeurIPS
Sehoon Kim, Amir Gholami, Albert E. Shaw, Nicholas Lee, Karttikeya Mangalam, Jitendra Malik, Michael W. Mahoney, Kurt Keutzer
2022 J jnl
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition.
CoRR
Sehoon Kim, Amir Gholami, Albert E. Shaw, Nicholas Lee, Karttikeya Mangalam, Jitendra Malik, Michael W. Mahoney, Kurt Keutzer
2022 J jnl
Structured Video Tokens @ Ego4D PNR Temporal Localization Challenge 2022.
CoRR
Elad Ben-Avraham, Roei Herzig, Karttikeya Mangalam, Amir Bar, Anna Rohrbach, Leonid Karlinsky, Trevor Darrell, Amir Globerson
2021 J jnl
Ego4D: Around the World in 3, 000 Hours of Egocentric Video.
CoRR
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Christian Fuegen, Abrham Gebreselasie, Cristina González, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jáchym Kolár, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran K. Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Yunyi Zhu, Pablo Arbeláez, David Crandall, Dima Damen, Giovanni Maria Farinella, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard A. Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik
2021 A* conf
From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting.
ICCV
Karttikeya Mangalam, Yang An, Harshayu Girase, Jitendra Malik
2021 J jnl
Improved Multiscale Vision Transformers for Classification and Detection.
CoRR
Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, Christoph Feichtenhofer
2021 A* conf
LOKI: Long Term and Key Intentions for Trajectory Prediction.
ICCV
Harshayu Girase, Haiming Gang, Srikanth Malla, Jiachen Li, Akira Kanehara, Karttikeya Mangalam, Chiho Choi
2021 J jnl
LOKI: Long Term and Key Intentions for Trajectory Prediction.
CoRR
Harshayu Girase, Haiming Gang, Srikanth Malla, Jiachen Li, Akira Kanehara, Karttikeya Mangalam, Chiho Choi
2021 A conf
Mitigating Mode Collapse by Sidestepping Catastrophic Forgetting.
BMVC
Karttikeya Mangalam, Rohin Garg
2021 A* conf
Multiscale Vision Transformers.
ICCV
Haoqi Fan, Bo Xiong, Karttikeya Mangalam, Yanghao Li, Zhicheng Yan, Jitendra Malik, Christoph Feichtenhofer
2021 J jnl
Multiscale Vision Transformers.
CoRR
Haoqi Fan, Bo Xiong, Karttikeya Mangalam, Yanghao Li, Zhicheng Yan, Jitendra Malik, Christoph Feichtenhofer
2021 J jnl
Object-Region Video Transformers.
CoRR
Roei Herzig, Elad Ben-Avraham, Karttikeya Mangalam, Amir Bar, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson
2021 J jnl
Overcoming Mode Collapse with Adaptive Multi Adversarial Training.
CoRR
Karttikeya Mangalam, Rohin Garg
2020 A conf
Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision.
WACV
Karttikeya Mangalam, Ehsan Adeli, Kuan-Hui Lee, Adrien Gaidon, Juan Carlos Niebles
2020 J jnl
From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting.
CoRR
Karttikeya Mangalam, Yang An, Harshayu Girase, Jitendra Malik
2020 — conf
It Is Not the Journey But the Destination: Endpoint Conditioned Trajectory Prediction.
ECCV (2)
Karttikeya Mangalam, Harshayu Girase, Shreyas Agarwal, Kuan-Hui Lee, Ehsan Adeli, Jitendra Malik, Adrien Gaidon
2020 J jnl
It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction.
CoRR
Karttikeya Mangalam, Harshayu Girase, Shreyas Agarwal, Kuan-Hui Lee, Ehsan Adeli, Jitendra Malik, Adrien Gaidon
2020 — conf
Long-Term Human Motion Prediction with Scene Context.
ECCV (1)
Zhe Cao, Hang Gao, Karttikeya Mangalam, Qi-Zhi Cai, Minh Vo, Jitendra Malik
2020 J jnl
Long-term Human Motion Prediction with Scene Context.
CoRR
Zhe Cao, Hang Gao, Karttikeya Mangalam, Qi-Zhi Cai, Minh Vo, Jitendra Malik
2019 J jnl
Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision.
CoRR
Karttikeya Mangalam, Ehsan Adeli, Kuan-Hui Lee, Adrien Gaidon, Juan Carlos Niebles
2018 A* conf
Future Person Localization in First-Person Videos.
CVPR
Takuma Yagi, Karttikeya Mangalam, Ryo Yonetani, Yoichi Sato
2018 A conf
Learning Spontaneity to Improve Emotion Recognition in Speech.
INTERSPEECH
Karttikeya Mangalam, Tanaya Guha
2018 J jnl
On Compressing U-net Using Knowledge Distillation.
CoRR
Karttikeya Mangalam, Mathieu Salzamann
2017 J jnl
Bitwise Operations of Cellular Automaton on Gray-scale Images.
CoRR
Karttikeya Mangalam, K. S. Venkatesh
2017 J jnl
Future Person Localization in First-Person Videos.
CoRR
Takuma Yagi, Karttikeya Mangalam, Ryo Yonetani, Yoichi Sato
2017 J jnl
Learning Spontaneity to Improve Emotion Recognition In Speech.
CoRR
Karttikeya Mangalam, Tanaya Guha