NeurIPS 2024

NeurIPS 2024 : 6 papers accepted!

Our team will be presenting the following works at the NeurIPS conference:

• [Spotlight] Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss by Paul Krzakala, Junjie Yang, Rémi Flamary, Florence d’Alché-Buc, Charlotte Laclau, Matthieu Labeau (arxiv paper)

• [Poster] Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families by François Bertholom, Randal Douc, François Roueff

• [Poster] Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing by David Perera, Victor Letzelter, Theo Mariotte, Adrien Cortes, Mickael Chen, Slim Essid, Gaël Richard (arxiv paper)

• [Poster] Implicit Bias of Mirror Flow on Separable Data by Scott Pesme, Radu-Alexandru Dragomir, Nicolas Flammarion (arxiv paper)

• [Poster] ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation by Cédric Rommel, Victor Letzelter, Nermin Samet, Renaud Marlet, Matthieu Cor, Patrick Perez, Eduardo Valle (arxiv paper)

• [Poster] An eye for an ear: zero-shot audio description leveraging an image captioner with audio-visual token distribution matching by Hugo Malard, Michel Olvera, Stéphane Lathuilière, Slim Essid (arxiv paper)