Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization.

Konstantinos Kallidromitis

Shufan Li Konstantinos Kallidromitis Akash Gokul Yuta Kyuragi Aditya Grover Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization. 2026 May abs/2605.29198 CoRR https://doi.org/10.48550/arXiv.2605.29198 db/journals/corr/corr2605.html#abs-2605-29198 streams/journals/corr

Dantong Niu Zhuoyang Liu Zekai Wang Boning Shao Zhao-Heng Yin Anirudh Pai Yuvan Sharma Stefano Saravalle Ruijie Zheng Jing Wang Ryan Punamiya Mengda Xu Yuqi Xie Yunfan Jiang 0001 Letian Fu Konstantinos Kallidromitis Matteo Gioia Junyi Zhang 0004 Jiaxin Ge Haiwen Feng Fabio Galasso Wei Zhan David M. Chan Yutong Bai Roei Herzig Jiahui Lei Li Fei-Fei 0001 Ken Goldberg Jitendra Malik Pieter Abbeel Yuke Zhu Danfei Xu Linxi Fan Trevor Darrell T-Rex: Tactile-Reactive Dexterous Manipulation. 2026 June abs/2606.17055 CoRR https://doi.org/10.48550/arXiv.2606.17055 db/journals/corr/corr2606.html#abs-2606-17055 streams/journals/corr

Yuvan Sharma Dantong Niu Anirudh Pai Zekai Wang Zhuoyang Liu Baifeng Shi Stefano Saravalle Boning Shao Ruijie Zheng Jing Wang Konstantinos Kallidromitis Yusuke Kato Fabio Galasso Yuke Zhu Danfei Xu Linxi "Jim" Fan Jitendra Malik Trevor Darrell Roei Herzig Contrastive Action-Image Pre-training for Visuomotor Control. 2026 June abs/2606.17256 CoRR https://doi.org/10.48550/arXiv.2606.17256 db/journals/corr/corr2606.html#abs-2606-17256 streams/journals/corr

Shufan Li Konstantinos Kallidromitis Akash Gokul Zichun Liao Yusuke Kato Kazuki Kozuka Aditya Grover OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows. 13178-13188 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Li_OmniFlow_Any-to-Any_Generation_with_Multi-Modal_Rectified_Flows_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.01230 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#LiKGLKKG25 Shufan Li Konstantinos Kallidromitis Akash Gokul Arsh Koneru Yusuke Kato Kazuki Kozuka Aditya Grover Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection. 2025 ICCV 15657-15668 conf/iccv/2025 https://doi.org/10.1109/ICCV51701.2025.01453 db/conf/iccv/iccv2025.html#LiKGKKKG25 streams/conf/iccv Xudong Wang 0007 Shaolun Zhang Shufan Li Kehan Li Konstantinos Kallidromitis Yusuke Kato Kazuki Kozuka Trevor Darrell SegLLM: Multi-round Reasoning Segmentation with Large Language Models. 2025 ICLR https://openreview.net/forum?id=Pm1NXHgzyf conf/iclr/2025 db/conf/iclr/iclr2025.html#0007ZLLKKKD25 Shufan Li Konstantinos Kallidromitis Hritik Bansal Akash Gokul Yusuke Kato Kazuki Kozuka Jason Kuen Zhe Lin Kai-Wei Chang 0001 Aditya Grover LaViDa: A Large Diffusion Language Model for Multimodal Understanding. 2025 NeurIPS http://papers.nips.cc/paper_files/paper/2025/hash/975affbe7b5f3b55fba62247b6877b1c-Abstract-Conference.html conf/nips/2025 db/conf/nips/neurips2025.html#LiKBGKKKLCG25

Shufan Li Konstantinos Kallidromitis Akash Gokul Arsh Koneru Yusuke Kato Kazuki Kozuka Aditya Grover Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection. 2025 March abs/2503.12271 CoRR https://doi.org/10.48550/arXiv.2503.12271 db/journals/corr/corr2503.html#abs-2503-12271 streams/journals/corr

Shufan Li Konstantinos Kallidromitis Hritik Bansal Akash Gokul Yusuke Kato Kazuki Kozuka Jason Kuen Zhe Lin Kai-Wei Chang 0001 Aditya Grover LaViDa: A Large Diffusion Language Model for Multimodal Understanding. 2025 May abs/2505.16839 CoRR https://doi.org/10.48550/arXiv.2505.16839 db/journals/corr/corr2505.html#abs-2505-16839 streams/journals/corr

Dantong Niu Yuvan Sharma Baifeng Shi Rachel Ding Matteo Gioia Haoru Xue Henry Tsai Konstantinos Kallidromitis Anirudh Pai Shankar Shastry Trevor Darrell Jitendra Malik Roei Herzig Learning to Grasp Anything by Playing with Random Toys. 2025 October abs/2510.12866 CoRR https://doi.org/10.48550/arXiv.2510.12866 db/journals/corr/corr2510.html#abs-2510-12866 streams/journals/corr

Yiming Qin Bomin Wei Jiaxin Ge Konstantinos Kallidromitis Stephanie Fu Trevor Darrell Xudong Wang 0007 Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens. 2025 November abs/2511.19418 CoRR https://doi.org/10.48550/arXiv.2511.19418 db/journals/corr/corr2511.html#abs-2511-19418 streams/journals/corr

Shufan Li Konstantinos Kallidromitis Akash Gokul Yusuke Kato Kazuki Kozuka Aditya Grover MobileWorldBench: Towards Semantic World Modeling For Mobile Agents. 2025 December abs/2512.14014 CoRR https://doi.org/10.48550/arXiv.2512.14014 db/journals/corr/corr2512.html#abs-2512-14014 streams/journals/corr

Paolo Mandica Luca Franco Konstantinos Kallidromitis Suzanne Petryk Fabio Galasso Hyperbolic Learning with Multimodal Large Language Models. 382-398 2024 ECCV Workshops (17) https://doi.org/10.1007/978-3-031-91585-7_23 conf/eccv/2024-w17 db/conf/eccv/eccv2024-w17.html#MandicaFKPG24 streams/conf/eccv Luca Franco Paolo Mandica Konstantinos Kallidromitis Devin Guillory Yu-Teng Li Trevor Darrell Fabio Galasso Hyperbolic Active Learning for Semantic Segmentation under Domain Shift. 2024 ICML https://proceedings.mlr.press/v235/franco24a.html https://openreview.net/forum?id=hKdJPMQvew conf/icml/2024 db/conf/icml/icml2024.html#FrancoMKGLDG24 13864-13884 Shufan Li Konstantinos Kallidromitis Akash Gokul Yusuke Kato Kazuki Kozuka Aligning Diffusion Models by Optimizing Human Utility. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/2c487f8a54cf24c0684c32abc77fed56-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#LiKGKK24

Shufan Li Konstantinos Kallidromitis Akash Gokul Yusuke Kato Kazuki Kozuka Aligning Diffusion Models by Optimizing Human Utility. 2024 abs/2404.04465 CoRR https://doi.org/10.48550/arXiv.2404.04465 db/journals/corr/corr2404.html#abs-2404-04465

Paolo Mandica Luca Franco Konstantinos Kallidromitis Suzanne Petryk Fabio Galasso Hyperbolic Learning with Multimodal Large Language Models. 2024 abs/2408.05097 CoRR https://doi.org/10.48550/arXiv.2408.05097 db/journals/corr/corr2408.html#abs-2408-05097 streams/journals/corr

Xudong Wang 0007 Shaolun Zhang Shufan Li Konstantinos Kallidromitis Kehan Li Yusuke Kato Kazuki Kozuka Trevor Darrell SegLLM: Multi-round Reasoning Segmentation. 2024 abs/2410.18923 CoRR https://doi.org/10.48550/arXiv.2410.18923 db/journals/corr/corr2410.html#abs-2410-18923 streams/journals/corr

Shufan Li Konstantinos Kallidromitis Akash Gokul Zichun Liao Yusuke Kato Kazuki Kozuka Aditya Grover OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows. 2024 abs/2412.01169 CoRR https://doi.org/10.48550/arXiv.2412.01169 db/journals/corr/corr2412.html#abs-2412-01169 streams/journals/corr

Xudong Wang 0007 Shufan Li Konstantinos Kallidromitis Yusuke Kato Kazuki Kozuka Trevor Darrell Hierarchical Open-vocabulary Universal Image Segmentation. 2023 NeurIPS http://papers.nips.cc/paper_files/paper/2023/hash/43663f64775ae439ec52b64305d219d3-Abstract-Conference.html conf/nips/2023 db/conf/nips/neurips2023.html#0007LKKKD23

Luca Franco Paolo Mandica Konstantinos Kallidromitis Devin Guillory Yu-Teng Li Fabio Galasso Hyperbolic Active Learning for Semantic Segmentation under Domain Shift. 2023 abs/2306.11180 CoRR https://doi.org/10.48550/arXiv.2306.11180 db/journals/corr/corr2306.html#abs-2306-11180

Xudong Wang 0007 Shufan Li Konstantinos Kallidromitis Yusuke Kato Kazuki Kozuka Trevor Darrell Hierarchical Open-vocabulary Universal Image Segmentation. 2023 abs/2307.00764 CoRR https://doi.org/10.48550/arXiv.2307.00764 db/journals/corr/corr2307.html#abs-2307-00764

Akash Gokul Konstantinos Kallidromitis Shufan Li Yusuke Kato Kazuki Kozuka Trevor Darrell Colorado J. Reed Refine and Represent: Region-to-Object Representation Learning. 2022 abs/2208.11821 CoRR https://doi.org/10.48550/arXiv.2208.11821 db/journals/corr/corr2208.html#abs-2208-11821

Konstantinos Kallidromitis Denis A. Gudovskiy Kazuki Kozuka Ohama Iku Luca Rigazio Contrastive Neural Processes for Self-Supervised Learning. 594-609 2021 ACML https://proceedings.mlr.press/v157/kallidromitis21a.html conf/acml/2021 db/conf/acml/acml2021.html#KallidromitisGK21

Konstantinos Kallidromitis Denis A. Gudovskiy Kazuki Kozuka Ohama Iku Luca Rigazio Contrastive Neural Processes for Self-Supervised Learning. 2021 abs/2110.13623 CoRR https://arxiv.org/abs/2110.13623 db/journals/corr/corr2110.html#abs-2110-13623

Pieter Abbeel Yutong Bai Hritik Bansal David M. Chan Kai-Wei Chang 0001 Trevor Darrell Rachel Ding Linxi FanLinxi "Jim" Fan Li Fei-Fei 0001 Haiwen Feng Luca Franco Letian Fu Stephanie Fu Fabio Galasso Jiaxin Ge Matteo Gioia Akash Gokul Kenneth Y. GoldbergKen Goldberg Aditya Grover Denis A. Gudovskiy Devin Guillory Roei Herzig Ohama Iku Yunfan Jiang 0001 Yusuke Kato Arsh Koneru Kazuki Kozuka Jason Kuen Yuta Kyuragi Jiahui Lei Kehan Li Shufan Li Yu-Teng Li Zichun Liao Zhe Lin Zhuoyang Liu Jitendra Malik Paolo Mandica Dantong Niu Anirudh Pai Suzanne Petryk Ryan Punamiya Yiming Qin Colorado ReedColorado J. Reed Luca Rigazio Stefano Saravalle Boning Shao Yuvan Sharma Shankar Shastry Baifeng Shi Henry Tsai Jing Wang Xudong Wang 0007 Zekai Wang Bomin Wei Yuqi Xie Danfei Xu Mengda Xu Haoru Xue Zhao-Heng Yin Wei Zhan Junyi Zhang 0004 Shaolun Zhang Ruijie Zheng Yuke Zhu