Nakul Agarwal

39 papers A* 9A 5Journal 21Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Learning Robust Reasoning through Guided Adversarial Self-Play.
CoRR
Shuozhe Li, Vaishnav Tadiparthi, Kwonjoon Lee, Nakul Agarwal, Hossein Nourkhiz Mahjoub, Ehsan Moradi-Pari, Lizhang Chen, Amy Zhang, Liu Leqi
2026 J jnl
MERGE: Guided Vision-Language Models for Multi-Actor Event Reasoning and Grounding in Human-Robot Interaction.
CoRR
Joerg Deigmoeller, Nakul Agarwal, Stephan Hasler, Daniel Tanneberg, Anna Belardinelli, Reza Ghoddoosian, Chao Wang, Felix Ocker, Fan Zhang, Behzad Dariush, Michael Gienger
2026 J jnl
Towards Driver Behavior Understanding: Weakly-Supervised Risk Perception in Driving Scenes.
CoRR
Nakul Agarwal, Yi-Ting Chen, Behzad Dariush
2025 A conf
ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos.
WACV
Reza Ghoddoosian, Nakul Agarwal, Isht Dwivedi, Behzad Darisuh
2025 J jnl
CARMA: Context-Aware Situational Grounding of Human-Robot Group Interactions by Combining Vision-Language Models with Object and Action Recognition.
CoRR
Joerg Deigmoeller, Stephan Hasler, Nakul Agarwal, Daniel Tanneberg, Anna Belardinelli, Reza Ghoddoosian, Chao Wang, Felix Ocker, Fan Zhang, Behzad Dariush, Michael Gienger
2025 A* conf
Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner.
ICML
Chunhui Zhang, Zhongyu Ouyang, Kwonjoon Lee, Nakul Agarwal, Sean Dae Houlihan, Soroush Vosoughi, Shao-Yuan Lo
2025 J jnl
Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner.
CoRR
Chunhui Zhang, Zhongyu Ouyang, Kwonjoon Lee, Nakul Agarwal, Sean Dae Houlihan, Soroush Vosoughi, Shao-Yuan Lo
2025 — conf
Pose-Aware Weakly-Supervised Action Segmentation.
CVPR Workshops
Zhihao Zhao, Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Behzad Dariush
2025 J jnl
Pose-Aware Weakly-Supervised Action Segmentation.
CoRR
Seth Z. Zhao, Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Behzad Dariush
2024 J jnl
ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos.
CoRR
Reza Ghoddoosian, Nakul Agarwal, Isht Dwivedi, Behzad Darisuh
2024 A* conf
AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
ICLR
Qi Zhao, Shijie Wang, Ce Zhang, Changcheng Fu, Minh Quan Do, Nakul Agarwal, Kwonjoon Lee, Chen Sun
2024 A* conf
Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models.
CVPR
Himangi Mittal, Nakul Agarwal, Shao-Yuan Lo, Kwonjoon Lee
2024 J jnl
Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models.
CoRR
Himangi Mittal, Nakul Agarwal, Shao-Yuan Lo, Kwonjoon Lee
2024 J jnl
Disentangled Neural Relational Inference for Interpretable Motion Prediction.
CoRR
Victoria Magdalena Dax, Jiachen Li, Enna Sachdeva, Nakul Agarwal, Mykel J. Kochenderfer
2024 J jnl
Disentangled Neural Relational Inference for Interpretable Motion Prediction.
IEEE Robotics Autom. Lett.
Victoria Magdalena Dax, Jiachen Li, Enna Sachdeva, Nakul Agarwal, Mykel J. Kochenderfer
2024 J jnl
IIT Bombay Racing Driverless: Autonomous Driving Stack for Formula Student AI.
CoRR
Yash Rampuria, Deep Boliya, Shreyash Gupta, Gopalan Iyengar, Ayush Rohilla, Mohak Vyas, Chaitanya Langde, Mehul Vijay Chanda, Ronak Gautam Matai, Kothapalli Namitha, Ajinkya Pawar, Bhaskar Biswas, Nakul Agarwal, Rajit Khandelwal, Rohan Kumar, Shubham Agarwal, Vishwam Patel, Abhimanyu Singh Rathore, Amna Rahman, Ayush Mishra, Yash Tangri
2024 — conf
M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models.
ECCV (14)
Seung-geun Chi, Hyung-Gun Chi, Hengbo Ma, Nakul Agarwal, Faizan Siddiqui, Karthik Ramani, Kwonjoon Lee
2024 J jnl
M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models.
CoRR
Seung-geun Chi, Hyung-Gun Chi, Hengbo Ma, Nakul Agarwal, Faizan Siddiqui, Karthik Ramani, Kwonjoon Lee
2024 A conf
Multi-Objective Recommendation via Multivariate Policy Learning.
RecSys
Olivier Jeunen, Jatin Mandav, Ivan Potapov, Nakul Agarwal, Sourabh Vaid, Wenzhe Shi, Aleksei Ustimenko
2024 J jnl
Multi-Objective Recommendation via Multivariate Policy Learning.
CoRR
Olivier Jeunen, Jatin Mandav, Ivan Potapov, Nakul Agarwal, Sourabh Vaid, Wenzhe Shi, Aleksei Ustimenko
2024 A conf
Object-centric Video Representation for Long-term Action Anticipation.
WACV
Ce Zhang, Changcheng Fu, Shijie Wang, Nakul Agarwal, Kwonjoon Lee, Chiho Choi, Chen Sun
2024 A conf
Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning.
WACV
Enna Sachdeva, Nakul Agarwal, Suhas Chundi, Sean Roelofs, Jiachen Li, Mykel J. Kochenderfer, Chiho Choi, Behzad Dariush
2024 A* conf
Uncertainty-aware Action Decoupling Transformer for Action Anticipation.
CVPR
Hongji Guo, Nakul Agarwal, Shao-Yuan Lo, Kwonjoon Lee, Qiang Ji
2024 — conf
Vamos: Versatile Action Models for Video Understanding.
ECCV (12)
Shijie Wang, Qi Zhao, Minh Quan Do, Nakul Agarwal, Kwonjoon Lee, Chen Sun
2023 A* conf
AdamsFormer for Spatial Action Localization in the Future.
CVPR
Hyung-Gun Chi, Kwonjoon Lee, Nakul Agarwal, Yi Xu, Karthik Ramani, Chiho Choi
2023 J jnl
AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
CoRR
Qi Zhao, Ce Zhang, Shijie Wang, Changcheng Fu, Nakul Agarwal, Kwonjoon Lee, Chen Sun
2023 A* conf
Latency Matters: Real-Time Action Forecasting Transformer.
CVPR
Harshayu Girase, Nakul Agarwal, Chiho Choi, Karttikeya Mangalam
2023 J jnl
Object-centric Video Representation for Long-term Action Anticipation.
CoRR
Ce Zhang, Changcheng Fu, Shijie Wang, Nakul Agarwal, Kwonjoon Lee, Chiho Choi, Chen Sun
2023 A* conf
Ordered Atomic Activity for Fine-grained Interactive Traffic Scenario Understanding.
ICCV
Nakul Agarwal, Yi-Ting Chen
2023 J jnl
Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning.
CoRR
Enna Sachdeva, Nakul Agarwal, Suhas Chundi, Sean Roelofs, Jiachen Li, Behzad Dariush, Chiho Choi, Mykel J. Kochenderfer
2023 J jnl
Vamos: Versatile Action Models for Video Understanding.
CoRR
Shijie Wang, Qi Zhao, Minh Quan Do, Nakul Agarwal, Kwonjoon Lee, Chen Sun
2023 A* conf
Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos.
ICCV
Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Behzad Dariush
2022 A* conf
Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos.
CVPR
Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Chiho Choi, Behzad Dariush
2022 J jnl
Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos.
CoRR
Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Chiho Choi, Behzad Dariush
2020 A conf
Unsupervised Domain Adaptation for Spatio-Temporal Action Localization.
BMVC
Nakul Agarwal, Yi-Ting Chen, Behzad Dariush, Ming-Hsuan Yang
2020 J jnl
Unsupervised Domain Adaptation for Spatio-Temporal Action Localization.
CoRR
Nakul Agarwal, Yi-Ting Chen, Behzad Dariush, Ming-Hsuan Yang
2018 J jnl
Connecting Visual Experiences using Max-flow Network with Application to Visual Localization.
CoRR
A. H. Abdul Hafez, Nakul Agarwal, C. V. Jawahar
2018 J jnl
Improving multiclass classification by deep networks using DAGSVM and Triplet Loss.
Pattern Recognit. Lett.
Nakul Agarwal, Vineeth N. Balasubramanian, C. V. Jawahar
2017 — conf
Real-Time Traffic Light Signal Recognition System for a Self-driving Car.
SIRS
Nakul Agarwal, Abhishek Sharma, Jieh-Ren Chang