I am a Full Professor and internationally recognized leader in artificial intelligence, machine learning, and computer vision, with demonstrated excellence bridging fundamental algorithmic research, applied systems, and research leadership. My research includes seminal contributions to multimodal AI, vision-language models, human behavior understanding, and probabilistic machine learning. I have successfully mentored PhD students and MS/undergraduate researchers, with graduates securing positions at leading institutions (Google, Meta, Amazon, Samsung) and faculty roles at top universities.
I currently serve as Program Chair for CVPR 2026, the world’s premier computer vision conference with over 16,000 submissions and 10,000+ expected international attendees. In this role, I am pioneering a Compute Reporting Initiative to promote transparency, sustainability, and accessibility in AI research—the first systematic effort at this scale in the AI community.
As Program Director at the National Science Foundation (2022-present, on leave from Rutgers), I oversee funding programs and develop new initiatives in AI and machine learning. I have co-developed major programs totaling over \$200M in funding, including cross-disciplinary programs: Mathematical Foundations of AI (MFAI) (\$8.5M flagship program advancing theoretical foundations), NSF Biofoundries (\$72M infrastructure initiative integrating AI with biological research), AI for Mathematical Reasoning (AIMing) (\$6M program bridging AI and mathematics communities), and Safe Learning-Enabled Systems (\$20M public-private partnership). I also lead the Research Experiences for Undergraduates (REU) initiative within CISE/IIS (\$84M overall program). My primary responsibility is managing Machine Learning programs within the Robust Intelligence initiative.
As Principal Scientist and Director at Samsung AI Center Cambridge, UK (2018-2021), I helped build and lead a team of 50 PhD-level researchers, scientists, and engineers developing cutting-edge AI technologies. Under my leadership, the team published 30+ papers at premier venues (CVPR, ICCV, ECCV, NeurIPS, ICML), filed 15+ patents, and successfully transferred multiple technologies into Samsung product divisions including mobile devices, digital appliances, and design.
My recent research advances the state-of-the-art in large vision-language models and multimodal AI systems, addressing critical challenges in hallucination detection, controllable generation, and visual reasoning. Notable publications include training-free approaches for detecting hallucinations in LVLMs (ICCV 2025), structured semantic augmentation for controllable image captioning (ECCV 2024), hierarchical VAE frameworks for visual puzzle generation (ICLR 2025), and cross-modal coherence methods (AAAI 2022). My collaborative reasoning work earned the Piero Zamperoni Best Student Paper Award (ICPR 2022). This research program spans deep learning for crowd analytics, representation learning and domain adaptation, computational nutrition, and visual reasoning—demonstrating breadth across fundamental algorithms and impactful applications.
At Rutgers University, I serve as member of the Center for Accelerated Real Time Analytics (CARTA) and member of the Executive Committee of Rutgers Center for Cognitive Science (RuCCS). I was also an associate faculty member of the Center for Quantitative Biology (CQB) and Management Science at Rutgers Business School.
My commitment to service and community leadership includes serving as Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence (2008-2013 and 2023-present, the highest-impact journal in AI/CS), Associate Editor-in-Chief for IPSJ Transactions on Computer Vision and Applications (2012-2022), Associate Editor for Image and Vision Computing Journal (2008-2026), and extensive service as Area Chair for CVPR, ICCV, ECCV, and other premier conferences. I have championed diversity and inclusion through long-term involvement with the Rutgers Future Scholars Program, Project RiSE, and the New Jersey Governor’s STEM Program, supporting students from underrepresented backgrounds in computing.
2025
- L. Che, T. Q. Liu, J. Jia, W. Qin, R. Tang, and V. Pavlovic, “Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs,” in Int’l Conference on Computer Vision, ICCV 2025, 2025.
[BibTeX] [Download PDF]@inproceedings{che2025iccv, title={Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs}, author={Liwei Che and Tony Qingze Liu and Jing Jia and Weiyi Qin and Ruixiang Tang and Vladimir Pavlovic}, year={2025}, booktitle = {Int'l Conference on Computer Vision, {ICCV} 2025}, month = {October}, eprint={2503.07772}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2503.07772}, } - X. Zhang, S. Wen, L. Han, F. Juefei, A. Srivastava, J. Huang, H. Wang, M. Tao, V. Pavlovic, and D. Metaxas, “SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models,” in IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025, 2025.
[BibTeX] [Download PDF]@inproceedings{zhang25wacv, author = {Xinxi Zhang and Song Wen and Ligong Han and Felix Juefei and Akash Srivastava and Junzhou Huang and Hao Wang and Molei Tao and Vladimir Pavlovic and Dimitris Metaxas}, title = {{SODA}: Spectral Orthogonal Decomposition Adaptation for Diffusion Models}, booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision, {WACV} 2025}, month = {February}, year = {2025}, url = {https://openaccess.thecvf.com/content/WACV2025/papers/Zhang_SODA_Spectral_Orthogonal_Decomposition_Adaptation_for_Diffusion_Models_WACV_2025_paper.pdf} } - K. Baisoti, P. Sahu, T. Q. Liu, Z. Xu, H. Wang, and V. Pavlovic, “GenVP: Generating Visual Puzzles With Contrastive Hierarchical VAEs,” in 13h International Conference on Learning Representations, ICLR 2025, 2025.
[BibTeX] [Download PDF]@inproceedings{basioti25iclr, author = {Kalliopi Baisoti and Pritish Sahu and Tony Qingze Liu and Zihao Xu and Hao Wang and Vladimir Pavlovic}, title = {{GenVP}: Generating Visual Puzzles With Contrastive Hierarchical {VAE}s}, booktitle = {13h International Conference on Learning Representations, {ICLR} 2025}, month = {April}, year = {2025}, url = {https://arxiv.org/pdf/2503.23598} } - L. Che, E. Tsamoura, and V. Pavlovic, “PLOG-PLL: Improving Deep Partial Label Learning with Logical Constraints,” , 2025.
[BibTeX]@article{che25icml, author = {Liwei Che and Efthymia Tsamoura and Vladimir Pavlovic}, title = {PLOG-PLL: Improving Deep Partial Label Learning with Logical Constraints}, journal = {}, year = {2025}, note = {Under review} }
2024
- A. Mrdović, S. Moon, S. Yoon, M. Kapadia, and V. Pavlovic, “ConsSeg: Accelerating Diffusion Model-based Semantic Segmentation with Consistency Models,” , 2024.
[BibTeX]@article{mrdovic24neurips, author = {Alen Mrdovi\'c and Seonghyeon Moon and Sejong Yoon and Mubbasir Kapadia and Vladimir Pavlovic}, title = {ConsSeg: Accelerating Diffusion Model-based Semantic Segmentation with Consistency Models}, journal = {}, year = {2024}, note = {Under review} } - J. Li and V. Pavlovic, “Box2Flow: Instance-based Action Flow Graphs from Videos,” in 27th International Conference on Pattern Recognition, ICPR 2024, 2024.
[BibTeX]@inproceedings{li24icpr, author = {Jiatong Li and Vladimir Pavlovic}, title = {{Box2Flow}: Instance-based Action Flow Graphs from Videos}, booktitle = {27th International Conference on Pattern Recognition, {ICPR} 2024}, month = {Dec}, year = {2024} } - K. Basioti, P. Sahu, T. Q. Liu, Z. Xu, H. Wang, and V. Pavlovic, “Generative Visual Puzzles with Global-Local Masked Contrastive HVAEs,” , 2024.
[BibTeX]@article{basioti24neurips, author = {Kalliopi Basioti and Pritish Sahu and Tony Qingze Liu and Zihao Xu and Hao Wang and Vladimir Pavlovic}, title = {Generative Visual Puzzles with Global-Local Masked Contrastive {HVAE}s}, journal = {}, year = {2024}, note = {Under review} } - T. Q. Liu, D. Li, S. S. Sohn, S. Yoon, M. Kapadia, and V. Pavlovic, “TrajDiffuse: A Conditional Diffusion Model for Environment-Aware Trajectory Prediction,” in 27th International Conference on Pattern Recognition, ICPR 2024, 2024.
[BibTeX]@inproceedings{liu24icpr, author = {Tony Qingze Liu and Danrui Li and Samuel S. Sohn and Sejong Yoon and Mubbasir Kapadia and Vladimir Pavlovic}, title = {{TrajDiffuse}: A Conditional Diffusion Model for Environment-Aware Trajectory Prediction}, booktitle = {27th International Conference on Pattern Recognition, {ICPR} 2024}, month = {Dec}, year = {2024} } - K. Basioti, M. A. Abdelsalam, F. Fancellu, V. Pavlovic, and A. Fazly, “CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation,” in European Conference on Computer Vision, ECCV, 2024.
[BibTeX] [Download PDF]@inproceedings{basioti24eccv, title = {{CIC-BART-SSA}: Controllable Image Captioning with Structured Semantic Augmentation}, author = {Kalliopi Basioti and Mohamed A. Abdelsalam and Federico Fancellu and Vladimir Pavlovic and Afsaneh Fazly}, booktitle = {European Conference on Computer Vision, {ECCV}}, year = {2024}, url = {http://arxiv.org/abs/2407.11393} } - C. Chang, D. Li, D. Patel, P. Goel, H. Zhou, S. Moon, S. S. Sohn, S. Yoon, V. Pavlovic, and M. Kapadia, “Learning from Synthetic Human Group Activities,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, p. 21922–21932.
[BibTeX] [Download PDF]@inproceedings{Chang_2024_CVPR, author = {Chang, Che-Jui and Li, Danrui and Patel, Deep and Goel, Parth and Zhou, Honglu and Moon, Seonghyeon and Sohn, Samuel S. and Yoon, Sejong and Pavlovic, Vladimir and Kapadia, Mubbasir}, title = {Learning from Synthetic Human Group Activities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21922--21932}, url = {https://openaccess.thecvf.com/content/CVPR2024/html/Chang_Learning_from_Synthetic_Human_Group_Activities_CVPR_2024_paper.html} }
2023
- Y. Wang, V. Ilic, J. Li, B. Kisavcanin, and V. Pavlovic, “ALWOD: Active Learning for Weakly-Supervised Object Detection,” in IEEE International Conference on Computer Vision, ICCV, 2023.
[BibTeX] [Download PDF]@inproceedings{Wang2023ALWODAL, title = {ALWOD: Active Learning for Weakly-Supervised Object Detection}, author = {Yuting Wang and Velibor Ilic and Jiatong Li and Branislav Kisa\vcanin and Vladimir Pavlovic}, booktitle = {{IEEE} International Conference on Computer Vision, {ICCV}}, year = {2023}, url = {https://api.semanticscholar.org/CorpusID:261822475} } - S. Moon, S. S. Sohn, H. Zhou, S. Yoon, V. Pavlovic, M. H. Khan, and M. Kapadia, “MSI: Maximize Support-Set Information for Few-Shot Segmentation,” in IEEE International Conference on Computer Vision, ICCV, 2023.
[BibTeX] [Download PDF]@inproceedings{Moon2023MSI, title = {MSI: Maximize Support-Set Information for Few-Shot Segmentation}, author = {Seonghyeon Moon and Samuel S. Sohn and Honglu Zhou and Sejong Yoon and Vladimir Pavlovic and Muhammad Haris Khan and Mubbasir Kapadia}, booktitle = {{IEEE} International Conference on Computer Vision, {ICCV}}, year = {2023}, url = {https://arxiv.org/abs/2212.04673} } - P. Sahu, K. Basioti, and A. M. V. Pavlovic, “Spatially Attentive Transformers for Abstract Visual Reasoning,” IEEE Transactions on Neural Networks and Learning Systems, 2023.
[BibTeX]@article{sahu23tnnls, author = {Pritish Sahu and Kalliopi Basioti and Alen Mrdovi\'c Vladimir Pavlovic}, title = {Spatially Attentive Transformers for Abstract Visual Reasoning}, journal = {{IEEE} Transactions on Neural Networks and Learning Systems}, year = {2023}, note = {Under review} } - M. Lee, S. S. Sohn, S. Moon, T. Q. Liu, S. Yoon, M. Kapadia, and V. Pavlovic, “MUSE-VAE-N: Multi-Scale VAE for Environment and Neighbor-Aware Trajectory Prediction,” IEEE Transactions on Pattern Recognition and Machine Learning, 2023.
[BibTeX]@article{lee23tpami, author = {Mihee Lee and Samuel S. Sohn and Seonghyeon Moon and Tony Q. Liu and Sejong Yoon and Mubbasir Kapadia and Vladimir Pavlovic}, title = {MUSE-VAE-N: Multi-Scale VAE for Environment and Neighbor-Aware Trajectory Prediction}, journal = {{IEEE} Transactions on Pattern Recognition and Machine Learning}, year = {2023}, note = {Under review} } - J. Wang, D. Massiceti, X. Hu, V. Pavlovic, and T. Lukasiewicz, “NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation,” in ICML 2023, 2023.
[BibTeX] [Download PDF]@inproceedings{wang2023np-semiseg, author = {Wang, Jianfeng and Massiceti, Daniela and Hu, Xiaolin and Pavlovic, Vladimir and Lukasiewicz, Thomas}, title = {NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation}, booktitle = {ICML 2023}, year = {2023}, month = {June}, url = {https://www.microsoft.com/en-us/research/publication/np-semiseg-when-neural-processes-meet-semi-supervised-semantic-segmentation/} } - K. Hu, B. M. Haworth, G. Berseth, V. Pavlovic, P. Faloutsos, and M. Kapadia, “Heterogeneous Crowd Simulation Using Parametric Reinforcement Learning,” IEEE Trans. Vis. Comput. Graph., vol. 29, iss. 4, p. 2036–2052, 2023. doi:10.1109/TVCG.2021.3139031
[BibTeX] [Download PDF]@article{HuHBPFK23, author = {Kaidong Hu and M. Brandon Haworth and Glen Berseth and Vladimir Pavlovic and Petros Faloutsos and Mubbasir Kapadia}, title = {Heterogeneous Crowd Simulation Using Parametric Reinforcement Learning}, journal = {{IEEE} Trans. Vis. Comput. Graph.}, volume = {29}, number = {4}, pages = {2036--2052}, year = {2023}, url = {https://doi.org/10.1109/TVCG.2021.3139031}, doi = {10.1109/TVCG.2021.3139031}, timestamp = {Sat, 11 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tvcg/HuHBPFK23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } - G. Lin, J. Y. Li, A. Fazly, V. Pavlovic, and K. N. Truong, “Identifying Multimodal Context Awareness Requirements for Supporting User Interaction with Procedural Videos,” in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, CHI 2023, Hamburg, Germany, April 23-28, 2023, 2023, p. 761:1–761:17. doi:10.1145/3544548.3581006
[BibTeX] [Download PDF]@inproceedings{LinLF0T23, author = {Georgianna Lin and Jin Yi Li and Afsaneh Fazly and Vladimir Pavlovic and Khai N. Truong}, editor = {Albrecht Schmidt and Kaisa V{\"{a}}{\"{a}}n{\"{a}}nen and Tesh Goyal and Per Ola Kristensson and Anicia Peters and Stefanie Mueller and Julie R. Williamson and Max L. Wilson}, title = {Identifying Multimodal Context Awareness Requirements for Supporting User Interaction with Procedural Videos}, booktitle = {Proceedings of the 2023 {CHI} Conference on Human Factors in Computing Systems, {CHI} 2023, Hamburg, Germany, April 23-28, 2023}, pages = {761:1--761:17}, publisher = {{ACM}}, year = {2023}, url = {https://doi.org/10.1145/3544548.3581006}, doi = {10.1145/3544548.3581006}, timestamp = {Sat, 29 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/chi/LinLF0T23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } - Y. Wang, R. Guerrero, and V. Pavlovic, “D\(^\mbox2\)F2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation,” in IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Waikoloa, HI, USA, January 2-7, 2023, 2023, p. 22–31. doi:10.1109/WACV56688.2023.00011
[BibTeX] [Download PDF]@inproceedings{WangGP23, author = {Yuting Wang and Ricardo Guerrero and Vladimir Pavlovic}, title = {D\({}^{\mbox{2}}\)F2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation}, booktitle = {{IEEE/CVF} Winter Conference on Applications of Computer Vision, {WACV} 2023, Waikoloa, HI, USA, January 2-7, 2023}, pages = {22--31}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/WACV56688.2023.00011}, doi = {10.1109/WACV56688.2023.00011}, timestamp = {Tue, 14 Feb 2023 22:26:55 +0100}, biburl = {https://dblp.org/rec/conf/wacv/WangGP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } - C. -, H. Zhou, P. Goel, A. Bhat, S. Moon, S. S. Sohn, S. Yoon, V. Pavlovic, and M. Kapadia, “Learning from Synthetic Human Group Activities,” CoRR, vol. abs/2306.16772, 2023. doi:10.48550/arXiv.2306.16772
[BibTeX] [Download PDF]@article{chang23arxiv, author = {Che{-}Jui Chang and Honglu Zhou and Parth Goel and Aditya Bhat and Seonghyeon Moon and Samuel S. Sohn and Sejong Yoon and Vladimir Pavlovic and Mubbasir Kapadia}, title = {Learning from Synthetic Human Group Activities}, journal = {CoRR}, volume = {abs/2306.16772}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.16772}, doi = {10.48550/arXiv.2306.16772}, eprinttype = {arXiv}, eprint = {2306.16772}, timestamp = {Mon, 03 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-16772.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } - M. Lee and V. Pavlovic, “Private-Shared Disentangled Multimodal VAE for Learning of Hybrid Latent Representations,” IEEE Transactions on Image Processing, 2023.
[BibTeX]@article{lee23tip, author = {Mihee Lee and Vladimir Pavlovic}, title = {Private-Shared Disentangled Multimodal {VAE} for Learning of Hybrid Latent Representations}, journal = {{IEEE} Transactions on Image Processing}, year = {2023}, note = {Under review} }