Skip to yearly menu bar Skip to main content


(3 events)   Timezone:  
Show all
Toggle Poster Visibility
Oral
Wed Dec 03 10:00 AM -- 10:20 AM (PST) @ Upper Level Ballroom 6AB None
Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
In Oral 1B Generation/Simulation 1
Ge Wu ⋅ Shen Zhang ⋅ Ruijing Shi ⋅ Shanghua Gao ⋅ Zhenyuan Chen ⋅ Lei Wang ⋅ Zhaowei Chen ⋅ Hongcheng Gao ⋅ Yao Tang ⋅ jian Yang ⋅ Ming-Ming Cheng ⋅ Xiang Li
[ OpenReview] 
Oral
Wed Dec 03 10:20 AM -- 10:40 AM (PST) @ Upper Level Ballroom 6AB None
On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
In Oral 1B Generation/Simulation 1
Quentin Bertrand ⋅ Anne Gagneux ⋅ Mathurin Massias ⋅ Rémi Emonet
[ OpenReview] 
Oral
Wed Dec 03 10:40 AM -- 11:00 AM (PST) @ Upper Level Ballroom 6AB None
Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training
In Oral 1B Generation/Simulation 1
Tony Bonnaire ⋅ Raphaël Urfin ⋅ Giulio Biroli ⋅ Marc Mezard
[ OpenReview]