51 citations · 51 across the 4 of their papers we have counts for
4 papers
Anchored Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models
Mariam Hassan, Bastien Van Delft, Wuyang Li +1
State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal…
LayerSync: Self-aligning Intermediate Layers
Yasaman Haghighi, Bastien van Delft, Mariam Hassan +1
We propose LayerSync, a domain-agnostic approach for improving the generation quality and the training efficiency of diffusion models. Prior studies have highlighted the connection…
CODE: Confident Ordinary Differential Editing
Bastien van Delft, Tommaso Martorella, Alexandre Alahi
Conditioning image generation facilitates seamless editing and the creation of photorealistic images. However, conditioning on noisy or Out-of-Distribution (OoD) images poses signi…
Estimating Risk and Uncertainty in Deep Reinforcement Learning
William R. Clements, Bastien Van Delft, Benoît-Marie Robaglia +2
Reinforcement learning agents are faced with two types of uncertainty. Epistemic uncertainty stems from limited data and is useful for exploration, whereas aleatoric uncertainty ar…