AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Haozhe Qi, Kevin Qu, Mahdi Rad, Rui Wang, Alexander Mathis, Marc Pollefeys
March 2026
arXiv | March 2026
Mahdi Rad
Senior Scientist
论文与出版物
-
-
-
Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
Kevin Qu, Haozhe Qi, Mihai Dusmanu, Mahdi Rad, Rui Wang, Marc Pollefeys
March 2026
arXiv | March 2026
-
-
-
EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models
Andy Bonnetto, Haozhe Qi, Franklin Leong, Matea Tashkovska, Mahdi Rad, S. Shokur, Friedhelm Hummel, S. Micera, Marc Pollefeys, Alexander Mathis
NeurIPS 2025 | June 2025
-
-
-
SIGMA: An Open-Source Interactive System for Mixed-Reality Task Assistance Research – Extended Abstract
Dan Bohus, Sean Andrist, Nick Saw, Ann Paradiso, Ishani Chakraborty, Mahdi Rad
2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) | March 2024, pp. 889-890
-
-
-
HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World
Xin Wang, Taein Kwon, Mahdi Rad, Bowen Pan, Ishani Chakraborty, Sean Andrist, Dan Bohus, Ashley Feniello, Felipe Vieira Frujeri, Neel Joshi, Marc Pollefeys
ICCV 2023 | September 2023
-
-
-
AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Haozhe Qi, Kevin Qu, Mahdi Rad, Rui Wang, Alexander Mathis, Marc Pollefeys
March 2026
arXiv | March 2026
-
SIGMA: An Open-Source Interactive System for Mixed-Reality Task Assistance Research – Extended Abstract
Dan Bohus, Sean Andrist, Nick Saw, Ann Paradiso, Ishani Chakraborty, Mahdi Rad
2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) | March 2024, pp. 889-890
-
HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World
Xin Wang, Taein Kwon, Mahdi Rad, Bowen Pan, Ishani Chakraborty, Sean Andrist, Dan Bohus, Ashley Feniello, Felipe Vieira Frujeri, Neel Joshi, Marc Pollefeys
ICCV 2023 | September 2023
-
-
-
Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
Kevin Qu, Haozhe Qi, Mihai Dusmanu, Mahdi Rad, Rui Wang, Marc Pollefeys
March 2026
arXiv | March 2026
-
EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models
Andy Bonnetto, Haozhe Qi, Franklin Leong, Matea Tashkovska, Mahdi Rad, S. Shokur, Friedhelm Hummel, S. Micera, Marc Pollefeys, Alexander Mathis
NeurIPS 2025 | June 2025
-
SIGMA: An Open-Source Interactive System for Mixed-Reality Task Assistance Research – Extended Abstract
Dan Bohus, Sean Andrist, Nick Saw, Ann Paradiso, Ishani Chakraborty, Mahdi Rad
2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) | March 2024, pp. 889-890
-
HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World
Xin Wang, Taein Kwon, Mahdi Rad, Bowen Pan, Ishani Chakraborty, Sean Andrist, Dan Bohus, Ashley Feniello, Felipe Vieira Frujeri, Neel Joshi, Marc Pollefeys
ICCV 2023 | September 2023
-
-
-
AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Haozhe Qi, Kevin Qu, Mahdi Rad, Rui Wang, Alexander Mathis, Marc Pollefeys
March 2026
arXiv | March 2026
-
Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
Kevin Qu, Haozhe Qi, Mihai Dusmanu, Mahdi Rad, Rui Wang, Marc Pollefeys
March 2026
arXiv | March 2026
-
-
-
EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models
Andy Bonnetto, Haozhe Qi, Franklin Leong, Matea Tashkovska, Mahdi Rad, S. Shokur, Friedhelm Hummel, S. Micera, Marc Pollefeys, Alexander Mathis
NeurIPS 2025 | June 2025
-
HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World
Xin Wang, Taein Kwon, Mahdi Rad, Bowen Pan, Ishani Chakraborty, Sean Andrist, Dan Bohus, Ashley Feniello, Felipe Vieira Frujeri, Neel Joshi, Marc Pollefeys
ICCV 2023 | September 2023
-
-
-
SIGMA: An Open-Source Interactive System for Mixed-Reality Task Assistance Research – Extended Abstract
Dan Bohus, Sean Andrist, Nick Saw, Ann Paradiso, Ishani Chakraborty, Mahdi Rad
2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) | March 2024, pp. 889-890
-