Auditing AI peer reviewers: a dose-response and false-positive benchmark on real scientific papers

Íñigo Zubeldia, Boris Bolliet, Francisco Villaescusa, Pablo Villanueva-Domingo and 1 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

Linear approximations to HMM filtering

Andrew Mah, Joshua L Pughe-Sanford, Sarah Harvey, Alex Williams

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Taking the Road Less Scheduled with Adaptive Polyak Steps

Adaptive Polyak step sizes for Schedule-Free SGD and Adam compute iteration-wise learning rates from losses and gradients, achieving anytime convergence without tuning base rates or horizons.

Dimitris Oikonomou, Matthew Buchholz, Yuen-Man Pun, Robert Gower and 1 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization

EmbedOpt steers protein diffusion by optimizing conditional embeddings rather than atomic coordinates, improving robustness and cryo-EM fitting performance.

Minhuan Li, Jiequn Han, Pilar Cossio, Luhuan Wu

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Muon Does Not Converge on Convex Lipschitz Functions

Muon fails to converge on convex Lipschitz functions under any learning rate schedule, though error feedback restores convergence yet harms practical performance. Convex Lipschitz theory therefore poorly explains Muon's practical success, which likely relies on smoothness.

Tetiana Parshakova, Ahmed Khaled, Michael Crawshaw, Guillaume Garrigos and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026