Improved Algorithms for Online Classification with Surrogate Losses

Abed Razawy, Valentina Masarotto, Dirk van der Hoeven

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?

Luc Sträter, Hazel Doughty

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization

PRO closes the indexing-decoding gap in multimodal generative retrieval via prefix ranking distillation, vocabulary scheduling, and geometric score fusion to improve beam search retention and retrieval accuracy.

Yufei Chen, Zihan Wang, Yubao Tang, Yukun Zhao and 2 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective

Treating neural quantum state optimization as advantage policy-gradient enables PWO, a trust-region algorithm that improves stability and scales to 1.5B parameters.

Juan A Duque, Sergio García Heredia, Vinicius Hernandes, Eliska Greplova and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Data-Driven Covariate Selection for Nonparametric and Cycle-Agnostic Causal Effect Estimation

Local data-driven covariate selection via conditional independence remains sound and complete in cyclic causal models, enabling unified cycle-agnostic causal effect estimation.

Ana L Vicente, Gijs van Seeventer, Saber Salehkaleybar

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026