10 Hi! PARIS Papers Accepted at ICCV 2025
From October 19 to 25, Hi! PARIS researchers will be in Honolulu, Hawaii, for the International Conference on Computer Vision (ICCV 2025), one of the most important gatherings worldwide in the field.
10 papers from Hi! PARIS affiliated teams have been accepted this year, a recognition of the quality of our work across partner institutions.
The accepted papers span a wide range of topics in computer vision: from efficient generative modeling (Di[M]O, LaCoOT) and advances in 3D understanding and shape analysis (ZeroKey, DiffuMatch, LACONIC), to multimodal and language-vision systems (FOLDER, Ask and Remember). Other works explore novel applications such as scientific video analysis (SciVid), collaborative navigation (Collaborative Instance Object Navigation), and even film-grammar–aware audio description (Shot-by-Shot).
With this strong presence at ICCV 2025, Hi! PARIS continues to contribute to the international conversation on the future of AI and computer vision, while staying true to its mission: advancing AI for science, business, and society.
Congratulations to our researchers!
Here is a list of papers accepted at ICML 2025 that include at least one author affiliated with Hi! PARIS:
| Title | Hi! PARIS Authors | All Authors |
|---|---|---|
| Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues | Gianni Franchi | Francesco Taioli, Edoardo Zorzi, Gianni Franchi, Alberto Castellini, Alessandro Farinelli, Marco Cristani, Yiming Wang |
| Di[M]O: Distilling Masked Diffusion Models into One-step Generator | Vicky Kalogeiton | Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière, Vicky Kalogeiton |
| LaCoOT: Layer Collapse through Optimal Transport | Enzo Tartaglione | Victor Quétu, Zhu Liao, Nour Hezbri, Fabio Pizzati, Enzo Tartaglione |
| Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering | Enzo Tartaglione | Imad Eddine Marouf, Enzo Tartaglione, Stéphane Lathuilière, Joost van de Weijer |
| FOLDER: Accelerating Multi-Modal Large Language Models with Enhanced Performance | Enzo Tartaglione | Haicheng Wang, Zhemeng Yu, Gabriele Spadaro, Chen Ju, Victor Quétu, Shuai Xiao, Enzo Tartaglione |
| DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matching | Maks Ovsjanikov | Emery Pierson, Lei Li, Angela Dai, Maks Ovsjanikov |
| SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications | Maks Ovsjanikov | Yana Hasson, Pauline Luc, Liliane Momeni, Maks Ovsjanikov, Guillaume Le Moing, Alina Kuznetsova, Ira Ktena, Jennifer J. Sun, Skanda Koppula, Dilara Gokay, Joseph Heyward, Etienne Pot, Andrew Zisserman |
| LACONIC: A 3D Layout Adapter for Controllable Image Creation | Maks Ovsjanikov | Léopold Maillard, Tom Durand, Adrien Ramananarahary, Maks Ovsjanikov |
| ZeroKey: Point-Level Reasoning and Zero-Shot 3D Keypoint Detection from Large Language Models | Maks Ovsjanikov | Bingchen Gong, Diego Gomez, Abdullah Hamdi, Abdelrahman Eldesokey, Ahmed Abdelreheem, Peter Wonka, Maks Ovsjanikov |
| Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation | Gül Varol | Junyu Xie, Tengda Han, Max Bain, Arsha Nagrani, Eshika Khandelwal, Gül Varol, Weidi Xie, Andrew Zisserman |