Muhammad Jehanzeb Mirza

52 papers A* 9A 1C 1Journal 33Unranked 8

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	CALM: Class-Conditional Sparse Attention Vectors for Large Audio-Language Models. CoRR Videet Mehta, Liming Wang, Hilde Kuehne, Rogério Feris, James R. Glass, Muhammad Jehanzeb Mirza
2025	J	`jnl`	Can Diffusion Models Disentangle? A Theoretical Perspective. CoRR Liming Wang, Muhammad Jehanzeb Mirza, Yishu Gong, Yuan Gong, Jiaqi Zhang, Brian H. Tracey, Katerina Placek, Marco Vilela, James R. Glass
2025	A*	`conf`	Can We Talk Models Into Seeing the World Differently? ICLR Paul Gavrikov, Jovita Lukasik, Steffen Jung, Robert Geirhos, Muhammad Jehanzeb Mirza, Margret Keuper, Janis Keuper
2025	—	`conf`	Comparison Visual Instruction Tuning. CVPR Workshops Wei Lin, Muhammad Jehanzeb Mirza, Sivan Doveh, Rogério Feris, Raja Giryes, Sepp Hochreiter, Leonid Karlinsky
2025	—	`conf`	Exploring Modality Guidance to Enhance VFM-based Feature Fusion for UDA in 3D Semantic Segmentation. CVPR Workshops Johannes Spöcklberger, Wei Lin, Pedro Hermosilla, Sivan Doveh, Horst Possegger, Muhammad Jehanzeb Mirza
2025	J	`jnl`	Exploring Modality Guidance to Enhance VFM-based Feature Fusion for UDA in 3D Semantic Segmentation. CoRR Johannes Spöcklberger, Wei Lin, Pedro Hermosilla, Sivan Doveh, Horst Possegger, Muhammad Jehanzeb Mirza
2025	J	`jnl`	GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models. Trans. Mach. Learn. Res. Muhammad Jehanzeb Mirza, Mengjie Zhao, Zhuoyuan Mao, Sivan Doveh, Wei Lin, Paul Gavrikov, Michael Dorkenwald, Shiqi Yang, Saurav Jha, Hiromi Wakaki, Yuki Mitsufuji, Horst Possegger, Rogério Feris, Leonid Karlinsky, James R. Glass
2025	J	`jnl`	Instructify: Demystifying Metadata to Visual Instruction Tuning Data Conversion. CoRR Jacob A. Hansen, Wei Lin, Junmo Kang, Muhammad Jehanzeb Mirza, Hongyin Luo, Rogério Feris, Alan Ritter, James R. Glass, Leonid Karlinsky
2025	J	`jnl`	KV Cache Steering for Inducing Reasoning in Small Language Models. CoRR Max Belitsky, Dawid Jan Kopiczko, Michael Dorkenwald, Muhammad Jehanzeb Mirza, Cees G. M. Snoek, Yuki M. Asano
2025	A*	`conf`	LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content. ICLR Nimrod Shabtay, Felipe Maia Polo, Sivan Doveh, Wei Lin, Muhammad Jehanzeb Mirza, Leshem Choshen, Mikhail Yurochkin, Yuekai Sun, Assaf Arbelle, Leonid Karlinsky, Raja Giryes
2025	A*	`conf`	Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models. ICLR Saurav Jha, Shiqi Yang, Masato Ishii, Mengjie Zhao, Christian Simon, Muhammad Jehanzeb Mirza, Dong Gong, Lina Yao, Shusuke Takahashi, Yuki Mitsufuji
2025	J	`jnl`	Overflow Prevention Enhances Long-Context Recurrent LLMs. CoRR Assaf Ben-Kish, Itamar Zimerman, Muhammad Jehanzeb Mirza, James R. Glass, Leonid Karlinsky, Raja Giryes
2025	J	`jnl`	PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies. CoRR Lukas Selch, Yufang Hou, Muhammad Jehanzeb Mirza, Sivan Doveh, James R. Glass, Rogério Feris, Wei Lin
2025	J	`jnl`	Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling. CoRR Saurav Jha, Muhammad Jehanzeb Mirza, Wei Lin, Shiqi Yang, Sarath Chandar
2025	J	`jnl`	Schrodinger Audio-Visual Editor: Object-Level Audiovisual Removal. CoRR Weihan Xu, Kan Jen Cheng, Koichi Saito, Muhammad Jehanzeb Mirza, Tingle Li, Yisi Liu, Alexander H. Liu, Liming Wang, Masato Ishii, Takashi Shibuya, Yuki Mitsufuji, Gopala Anumanchipalli, Paul Pu Liang
2025	J	`jnl`	TTRV: Test-Time Reinforcement Learning for Vision Language Models. CoRR Akshit Singh, Shyam Marjit, Wei Lin, Paul Gavrikov, Serena Yeung-Levy, Hilde Kuehne, Rogério Feris, Sivan Doveh, James R. Glass, Muhammad Jehanzeb Mirza
2025	—	`conf`	TTT-KD: Test-Time Training for 3D Semantic Segmentation Through Knowledge Distillation From Foundation Models. 3DV Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla
2025	J	`jnl`	VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes. CoRR Paul Gavrikov, Wei Lin, Muhammad Jehanzeb Mirza, Soumya Jahagirdar, Muhammad Huzaifa, Sivan Doveh, Serena Yeung-Levy, James R. Glass, Hilde Kuehne
2024	J	`jnl`	Are Vision Language Models Texture or Shape Biased and Can We Steer Them? CoRR Paul Gavrikov, Jovita Lukasik, Steffen Jung, Robert Geirhos, Bianca Lamm, Muhammad Jehanzeb Mirza, Margret Keuper, Janis Keuper
2024	J	`jnl`	Comparison Visual Instruction Tuning. CoRR Wei Lin, Muhammad Jehanzeb Mirza, Sivan Doveh, Rogério Feris, Raja Giryes, Sepp Hochreiter, Leonid Karlinsky
2024	A*	`conf`	ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs. NeurIPS Irene Huang, Wei Lin, Muhammad Jehanzeb Mirza, Jacob A. Hansen, Sivan Doveh, Victor Butoi, Roei Herzig, Assaf Arbelle, Hilde Kuehne, Trevor Darrell, Chuang Gan, Aude Oliva, Rogério Feris, Leonid Karlinsky
2024	J	`jnl`	ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs. CoRR Irene Huang, Wei Lin, Muhammad Jehanzeb Mirza, Jacob A. Hansen, Sivan Doveh, Victor Ion Butoi, Roei Herzig, Assaf Arbelle, Hilde Kuehne, Trevor Darrell, Chuang Gan, Aude Oliva, Rogério Feris, Leonid Karlinsky
2024	J	`jnl`	GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models. CoRR Muhammad Jehanzeb Mirza, Mengjie Zhao, Zhuoyuan Mao, Sivan Doveh, Wei Lin, Paul Gavrikov, Michael Dorkenwald, Shiqi Yang, Saurav Jha, Hiromi Wakaki, Yuki Mitsufuji, Horst Possegger, Rogério Feris, Leonid Karlinsky, James R. Glass
2024	J	`jnl`	Into the Fog: Evaluating Multiple Object Tracking Robustness. CoRR Nadezda Kirillova, Muhammad Jehanzeb Mirza, Horst Possegger, Horst Bischof
2024	A	`conf`	Into the Fog: Evaluating Robustness of Multiple Object Tracking. BMVC Nadezda Kirillova, Muhammad Jehanzeb Mirza, Horst Bischof, Horst Possegger
2024	J	`jnl`	LiveXiv - A Multi-Modal Live Benchmark Based on Arxiv Papers Content. CoRR Nimrod Shabtay, Felipe Maia Polo, Sivan Doveh, Wei Lin, Muhammad Jehanzeb Mirza, Leshem Choshen, Mikhail Yurochkin, Yuekai Sun, Assaf Arbelle, Leonid Karlinsky, Raja Giryes
2024	J	`jnl`	Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs. CoRR Muhammad Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Sivan Doveh, Jakub Micorek, Mateusz Kozinski, Hilde Kuehne, Horst Possegger
2024	—	`conf`	Meta-prompting for Automating Zero-Shot Visual Recognition with LLMs. ECCV (2) Muhammad Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Sivan Doveh, Jakub Micorek, Mateusz Kozinski, Hilde Kuehne, Horst Possegger
2024	J	`jnl`	Mining Your Own Secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models. CoRR Saurav Jha, Shiqi Yang, Masato Ishii, Mengjie Zhao, Christian Simon, Muhammad Jehanzeb Mirza, Dong Gong, Lina Yao, Shusuke Takahashi, Yuki Mitsufuji
2024	J	`jnl`	TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models. CoRR Lisa Weijler, Muhammad Jehanzeb Mirza, Leon Sick, Can Ekkazan, Pedro Hermosilla
2024	J	`jnl`	Teaching VLMs to Localize Specific Objects from In-context Examples. CoRR Sivan Doveh, Nimrod Shabtay, Wei Lin, Eli Schwartz, Hilde Kuehne, Raja Giryes, Rogério Feris, Leonid Karlinsky, James R. Glass, Assaf Arbelle, Shimon Ullman, Muhammad Jehanzeb Mirza
2024	J	`jnl`	Towards Multimodal In-Context Learning for Vision & Language Models. CoRR Sivan Doveh, Shaked Perek, Muhammad Jehanzeb Mirza, Amit Alfassy, Assaf Arbelle, Shimon Ullman, Leonid Karlinsky
2024	—	`conf`	Towards Multimodal In-context Learning for Vision and Language Models. ECCV Workshops (19) Sivan Doveh, Shaked Perek, Muhammad Jehanzeb Mirza, Wei Lin, Amit Alfassy, Assaf Arbelle, Shimon Ullman, Leonid Karlinsky
2023	A*	`conf`	ActMAD: Activation Matching to Align Distributions for Test-Time-Training. CVPR Muhammad Jehanzeb Mirza, Pol Jané-Soneira, Wei Lin, Mateusz Kozinski, Horst Possegger, Horst Bischof
2023	A*	`conf`	LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections. NeurIPS Muhammad Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Horst Possegger, Mateusz Kozinski, Rogério Feris, Horst Bischof
2023	J	`jnl`	LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections. CoRR Muhammad Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Mateusz Kozinski, Horst Possegger, Rogério Feris, Horst Bischof
2023	A*	`conf`	MATE: Masked Autoencoders are Online 3D Test-Time Learners. ICCV Muhammad Jehanzeb Mirza, Inkyu Shin, Wei Lin, Andreas Schriebl, Kunyang Sun, Jaesung Choe, Mateusz Kozinski, Horst Possegger, In So Kweon, Kuk-Jin Yoon, Horst Bischof
2023	C	`conf`	Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions. IV Stefan Leitner, Muhammad Jehanzeb Mirza, Wei Lin, Jakub Micorek, Marc Masana, Mateusz Kozinski, Horst Possegger, Horst Bischof
2023	J	`jnl`	Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions. CoRR Stefan Leitner, Muhammad Jehanzeb Mirza, Wei Lin, Jakub Micorek, Marc Masana, Mateusz Kozinski, Horst Possegger, Horst Bischof
2023	J	`jnl`	TAP: Targeted Prompting for Task Adaptive Generation of Textual Training Instances for Visual Classification. CoRR Muhammad Jehanzeb Mirza, Leonid Karlinsky, Wei Lin, Horst Possegger, Rogério Feris, Horst Bischof
2023	—	`conf`	Test-Time Adversarial Detection and Robustness for Localizing Humans Using Ultra Wide Band Channel Impulse Responses. EUSIPCO Abhiram Kolli, Muhammad Jehanzeb Mirza, Horst Possegger, Horst Bischof
2023	A*	`conf`	Video Test-Time Adaptation for Action Recognition. CVPR Wei Lin, Muhammad Jehanzeb Mirza, Mateusz Kozinski, Horst Possegger, Hilde Kuehne, Horst Bischof
2022	J	`jnl`	ActMAD: Activation Matching to Align Distributions for Test-Time-Training. CoRR Muhammad Jehanzeb Mirza, Pol Jané-Soneira, Wei Lin, Mateusz Kozinski, Horst Possegger, Horst Bischof
2022	—	`conf`	An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions. CVPR Workshops Muhammad Jehanzeb Mirza, Marc Masana, Horst Possegger, Horst Bischof
2022	J	`jnl`	An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions. CoRR Muhammad Jehanzeb Mirza, Marc Masana, Horst Possegger, Horst Bischof
2022	J	`jnl`	MATE: Masked Autoencoders are Online 3D Test-Time Learners. CoRR Muhammad Jehanzeb Mirza, Inkyu Shin, Wei Lin, Andreas Schriebl, Kunyang Sun, Jaesung Choe, Horst Possegger, Mateusz Kozinski, In So Kweon, Kuk-Jin Yoon, Horst Bischof
2022	J	`jnl`	Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses. CoRR Abhiram Kolli, Muhammad Jehanzeb Mirza, Horst Possegger, Horst Bischof
2022	A*	`conf`	The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization. CVPR Muhammad Jehanzeb Mirza, Jakub Micorek, Horst Possegger, Horst Bischof
2022	J	`jnl`	Video Test-Time Adaptation for Action Recognition. CoRR Wei Lin, Muhammad Jehanzeb Mirza, Mateusz Kozinski, Horst Possegger, Hilde Kuehne, Horst Bischof
2021	—	`conf`	Robustness of Object Detectors in Degrading Weather Conditions. ITSC Muhammad Jehanzeb Mirza, Cornelius Bürkle, Julio Jarquin, Michael Opitz, Fabian Oboril, Kay-Ulrich Scholl, Horst Bischof
2021	J	`jnl`	Robustness of Object Detectors in Degrading Weather Conditions. CoRR Muhammad Jehanzeb Mirza, Cornelius Bürkle, Julio Jarquin, Michael Opitz, Fabian Oboril, Kay-Ulrich Scholl, Horst Bischof
2021	J	`jnl`	The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization. CoRR Muhammad Jehanzeb Mirza, Jakub Micorek, Horst Possegger, Horst Bischof