When Prompts Override Vision: Instruction-Induced Hallucinations in LVLMs

Pegah KHAYATAN, Jayneel Parekh, Arnaud Dapogny, Mustafa Shukor and 2 more

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

Routeability Before Routing: Routeability Audit Protocol (RAP) and RouteabilityBench for Audited LLM Model Selection

Yihang Lu, Denica Kjorvezir, Ana Gjorgjevikj, Carola Doerr and 1 more

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

Unbounded Streaming Text-To-Speech with Prefixed Sliding Window Attention

Théodor Lemerle, Diego Torres Guarin, Téo Guichoux, Nicolas Obin and 1 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

MID: Mask-Image Distributional Divergence for Evaluating Medical Image Segmentation

Vincenzo Marcianò, XIAOMING ZHANG, Gianluca Guglielmo, Sebastien Ourselin and 2 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling

A learning-augmented algorithm for unrelated-machine makespan scheduling uses heavy-job predictions to achieve (1+ε)-approximation that smoothly degrades to 2-approximation as error grows.

Kaito Baba, Evripidis Bampis, Georgios Mitropoulos

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

Diff-CA: Separating Common and Salient Factors with Diffusion Models

Diff-CA conditions diffusion models to decompose image representations into common and salient factors via weak supervision, achieving high-fidelity contrastive generation and editing with provable factorization identifiability.

Michaël Soumm, Alexandre Fournier Montgieux, Yunlong HE, Pietro Gori and 1 more

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

Likelihood-free inference of phylogenetic tree posterior distributions

A likelihood-free neural network estimates phylogenetic tree posteriors via sequence pair encodings and subtree merges, outperforming likelihood-based methods especially for intractable evolutionary models.

Luc Blassel, Noémie Sauvage, Pierre Barrat-Charlaix, Bastien Boussau and 2 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

It's All Training: A Fully Synthetic Single-Stage Recipe for LLMs

SYNTH is an open-source synthetic dataset derived from Wikipedia that collapses pre-, mid-, and post-training into one stage, training competitive small models with 10-140x fewer tokens and higher factual precision than web-crawled data.

Pierre-Carl Langlais, Pieter Delobelle, Yannick Detrois, Pavel Chizhov and 6 more

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

Missing data and cluster graphs: cluster-level missingness vs variable-level missingness

This paper compares cluster-level and variable-level missingness graphs to derive conditions for recovering joint distributions and macro causal effects from coarse missingness models.

Willow Scott, Eugenio Valdano, Charles Assaad

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

A multi-scale information geometry reveals the structure of mutual information in neural populations

A multi-scale Riemannian geometry extending Fisher information relates metric structure to mutual information and reveals visual cortex encoding features.

Simone Azeglio, Steeve Laquitaine, Ulisse Ferrari, Matthew Chalk

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