VL
Victor Letzelter
cs.LGstat.MLcs.AIcs.CVcs.CLcs.ROmath.PRcs.NEcs.SDeess.AS
On Valency
published · living versionsW_5txyfx4z·v1 · currentpublished
Preprints & journals
10 papers in the corpus · 2023–2026Shieldstral2607.25857v2 · Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli et al.2026 · 0 citationsarXiv
Robostral Navigate2607.20785v3 · Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra et al.2026 · 0 citationsarXiv
REPA-G: Test-Time Conditioning with Representation-Aligned Visual Features2602.03753v2 · Nicolas Sereyjol-Garros, Ellington Kirby, Victor Letzelter et al.2026 · 0 citationsarXiv
Multiple Choice Learning of Low-Rank Adapters for Language Modeling2507.10419v3 · Victor Letzelter, Hugo Malard, Mathieu Fontaine et al.2025 · 0 citationsarXiv
Winner-takes-all for Multivariate Probabilistic Time Series Forecasting2506.05515v2 · Adrien Cort'es, R'emi Rehm, Victor Letzelter2025 · 0 citationsarXiv
Annealed Winner-Takes-All for Motion Forecasting2409.11172v3 · Yihong Xu, Victor Letzelter, Mickael Chen et al.2024 · 5 citationsarXiv
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing2407.15580v3 · David Perera, Victor Letzelter, Th'eo Mariotte et al.2024 · 2 citationsarXiv
Winner-takes-all learners are geometry-aware conditional density estimators2406.04706v1 · Victor Letzelter, David Perera, C'edric Rommel et al.2024 · 0 citationsarXiv
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation2312.06386v2 · C'edric Rommel, Victor Letzelter, Nermin Samet et al.2023 · 4 citationsarXiv
Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis2311.01052v2 · Victor Letzelter, Mathieu Fontaine, Mickael Chen et al.2023 · 2 citationsAdvances in neural information processing systems, Dec 2023, New Orleans, United States
Career total: 12 works. 10 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.