1 citations · 2 across the 13 of their papers we have counts for
14 papers
DualHeads: Reward-tilted few-step diffusion made simple
Yuanzhi Zhu, Eleftherios Tsonis, Simo Alami Chehboune +3
Distilled diffusion models generate high-quality images in a few sampling steps, but aligning them with task requirements and human preferences is difficult. Methods developed for…
TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film
Kaishuu Shinozaki-Conefrey, Olivier Pascaud, Robin Courant +3
Films communicate through deliberate creative choices, including lighting, color, composition, editing, dialogue, music, and sound. Humans naturally interpret these signals as dire…
What Images Cannot Say: Language-Guided Olfactory Representation Learning
Eleftherios Tsonis, Xi Wang, Vicky Kalogeiton
Images tell us what a scene looks like, but rarely what it would feel like to be there. While recent datasets pair visual scenes with electronic-nose measurements, aligning smell s…
SF20K Competition 2025: Summary and findings
Ridouane Ghermi, Xi Wang, Vicky Kalogeiton +1
This report presents the results and findings of the first edition of the Short-Films 20K (SF20K) Competition, held in conjunction with the SLoMO Workshop at ICCV 2025. The competi…
Diffusion Reinforcement Learning via Centered Reward Distillation
Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière +1
Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional corre…
What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards
Minh-Quan Le, Yuanzhi Zhu, Vicky Kalogeiton +1
Recent video diffusion models can synthesize visually compelling clips, yet often violate basic physical laws-objects float, accelerations drift, and collisions behave inconsistent…
MUSE: Manipulating Unified Framework for Synthesizing Emotions in Images via Test-Time Optimization
Yingjie Xia, Xi Wang, Jinglei Shi +2
Images evoke emotions that profoundly influence perception, often prioritized over content. Current Image Emotional Synthesis (IES) approaches artificially separate generation and…
One-step Diffusion Models with Bregman Density Ratio Matching
Yuanzhi Zhu, Eleftherios Tsonis, Lucas Degeorge +1
Diffusion and flow models achieve high generative quality but remain computationally expensive due to slow multi-step sampling. Distillation methods accelerate them by training fas…
Pulp Motion: Framing-aware multimodal camera and human motion generation
Robin Courant, Xi Wang, David Loiseaux +2
Treating human motion and camera trajectory generation separately overlooks a core principle of cinematography: the tight interplay between actor performance and camera work in the…
Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings
Yuanzhi Zhu, Xi Wang, Stéphane Lathuilière +1
One-step generators distilled from Masked Diffusion Models (MDMs) compress multiple sampling steps into a single forward pass, enabling efficient text and image synthesis. However,…
Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation
Yasser Benigmim, Subhankar Roy, Khalid Oublal +4
The rise of Artificial Intelligence as a Service (AIaaS) democratizes access to pre-trained models via Application Programming Interfaces (APIs), but also raises a fundamental ques…
FakeParts: a New Family of AI-Generated DeepFakes
Ziyi Liu, Firas Gabetni, Awais Hussain Sani +5
We introduce FakeParts, a new class of deepfakes characterized by subtle, localized manipulations to specific spatial regions or temporal segments of otherwise authentic videos. Un…
Collaborating Foundation Models for Domain Generalized Semantic Segmentation
Yasser Benigmim, Subhankar Roy, Slim Essid +2
Domain Generalized Semantic Segmentation (DGSS) deals with training a model on a labeled source domain with the aim of generalizing to unseen domains during inference. Existing DGS…
One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models
Yasser Benigmim, Subhankar Roy, Slim Essid +2
Adapting a segmentation model from a labeled source domain to a target domain, where a single unlabeled datum is available, is one the most challenging problems in domain adaptatio…