Skip to yearly menu bar Skip to main content


(3 events)   Timezone:  
Show all
Toggle Poster Visibility
Mexico City Oral
Wed Dec 03 10:00 AM -- 10:20 AM (PST) @ Don Alberto 2 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
Mexico City Oral
Wed Dec 03 10:20 AM -- 10:40 AM (PST) @ Don Alberto 2 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
Mexico City Oral
Wed Dec 03 10:40 AM -- 11:00 AM (PST) @ Don Alberto 2 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