Yo-ByT5: Efficient and High-Fidelity Diacritic Restoration for Yorùbá

Yo-ByT5 is a byte-level Yorùbá diacritic restoration model matching mT5-base accuracy with half the parameters and superior text fidelity.

Ahmad Samuel Gali, Shamsuddeen Hassan Muhammad

Published Oct 1, 2026 · 0 citations

Tail-Influence Sampling for CVaR Policy Evaluation

Tail-Influence Sampling allocates evaluation budgets by tail influence to estimate CVaR with oracle variance and lower MSE than rollouts.

Pauline Bourigault, Xiaotong Ji, Matthieu Zimmer, Rasul Tutunov and 1 more

Published Sep 29, 2026 · 0 citations · ▲ 27 on Hugging Face · Code ★ 1

FogGS: Physics-Grounded 3D Foggy Effects

Jiaxin LI, Tailin Wu, Jiankang Deng, Li Zhang and 1 more

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

FireMPC: A Multi-Source Pan-Canadian Wildfire Benchmark Revealing Spatiotemporal Generalization Gaps

Zhengsen Xu, Sibo Cheng, Lanying Wang, Aryan Sharma and 1 more

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

3D Molecule Generation from Rigid Motifs via $\mathrm{SE}(3)$ Flows

Roman Poletukhin, Marcel Kollovieh, Eike S. Eberhard, Stephan Günnemann

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

STEER: Route-Aware Adaptive Reasoning for Autonomous Driving

yangang Zou, Pei Liu, Nan Song, Bozhou Zhang and 5 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Practical Non-Stationary Graph Gaussian Processes

Senanayak Sesh Kumar Karri, Viacheslav (Slava) Borovitskiy

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

Gibbs Gradient Descent: A Langevin Approach to Optimization

Oussama Zekri, Anna Korba, Nicolas Boulle

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

HaNDF: Object-Conditioned Geometric Neural Hand Distance Fields

Zuhao Liu, Melih Darcan, Zhengdi Yu, Riza Alp Guler and 1 more

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

Beyond Ground Truth: Evaluating Non-Verifiable Reasoning in LLMs through Moral Robustness

Elizaveta Tennant, Benjamin Henke, Anita Keshmirian, Murray Shanahan and 4 more

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

MedFlowBench: Auditing Medical Agents in Full-Study Workflows

Weixiang Shen, Chengzhi Shen, Che Liu, Junde Wu and 10 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Reconciling Operational Energy Trilemma: A Heterogeneous Risk-Constrained MDP Framework with Residual Policy Learning

Yujian Ye, Siqi Qian, Yizhi Wu, Tianxiang Cui and 1 more

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

Outlier-Robust Multi-Output Gaussian Processes

Joshua Rooijakkers, Leiv Rønneberg, Francois-Xavier Briol, Jeremias Knoblauch and 1 more

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

Plausible Biomolecular Structure Prediction via Physics-informed Reinforcement Learning

Tai Dang, Hieu Tran, Long-Hung Pham, Sang Truong and 3 more

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

Certification-Enhanced Generalization Bounds

Leo Elmecker-Plakolm, Matthew R Wicker

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

Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning

Zerui Chen, Changrui Chen, Fei Ni, Jiankang Deng

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

Sparsity for Free: A Budget-Induced Equilibrium in Joint Topology–Parameter Search

Marcel Mordarski, Daniel Budina, Benjamin Gras, Abdulrahman Shehata and 1 more

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

EnerGNN: Learning Optimization-Compatible Energy Functions for Exact Constrained Combinatorial Inference

Niki Triantafyllou, Maria Papathanasiou

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Random-Projection Tree Stein Variational Gradient Descent

Shishuo Guo, Xiaoyuan Cheng, Zhuo Sun

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

Why Routers Freeze: Infinite Width Learning Dynamics for Mixture of Experts

Anish Dhir, Volkan Cevher, Leena Chennuru Vankadara

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Casper: A Projection-Based Neurosymbolic Layer for Scalable & Guaranteed Constraint Satisfaction

Lohith Konathala, Luca Andolfi, Eleonora Giunchiglia

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

Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attributions

Toni Liu, Baran Zadeoğlu, Nicolas Boulle, Raphaël Sarfati and 2 more

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

End-to-End Verification of Neuro-symbolic Automata via Contrastive Logit-Gaps

Abdelrahman Hekal, Vasileios Manginas, Nikolaos Manginas, Alessio Lomuscio

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

Beyond Langevin: Sampling Multimodal Densities using the Witten Laplacian on 1-forms

Sahani Pathiraja, Panos Parpas

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

PACE: Progress Actively-internalized Conditioning Execution for Long-horizon Manipulation

Fei Ni, Zhuo Chen, Xianze Yao, Zerui Chen and 5 more

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

Mamba Flow Matching Neural Processes: Linear-Time Inference for Irregularly Observed Spatial Fields

Cosmo Santoni, Giovanni Charles, Timothy James Hitge, Oliver Watson and 1 more

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

Estimating Model-Level Membership Inference Vulnerability Without Reference Models

Euodia Dodd, Natasa Krco, Igor Shilov, Matthew R Wicker and 1 more

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

Complex Schrödinger Bridges

Dong-Sig Han, Tolga Birdal

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

Symmetry Guarantees Statistic Recovery in Variational Inference

Symmetry in variational inference forces approximate minimizers to recover target statistics under misspecification, unifying prior results and yielding new directional guarantees.

Daniel Marks, Dario Paccagnan, Mark van der Wilk

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

Steering Optimisation Trajectories in Diffusion Representation Learning

Diffusion autoencoders learn different latent structures via distinct optimization regimes, and SteeringDRL steers training toward disentanglement by targeting U-Net shortcuts and using a noise-level curriculum.

Rajat Rasal, Tian Xia, Avinash Kori, Ben Glocker

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

Random Neural Network Expressivity for Non-Linear Partial Differential Equations

Random neural networks approximate time-dependent Sobolev functions with dimension-free rate 1/2 and efficiently solve nonlinear porous medium and compressible Navier-Stokes equations.

Muhammed Ali Mehmood, Lukas Gonon

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

Aligning Flow Map Policies with Optimal $Q$-Guidance

Flow map policies learn multi-step jumps across flow dynamics for fast action generation, and FMQ adapts them via optimal closed-form Q-guidance to achieve state-of-the-art offline-to-online RL with 21.3% higher success rates.

Christos Ziakas, Alessandra Russo, Joey Bose

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Multi-Marginal Couplings for Metropolis--Hastings

Multi-marginal coupling of Metropolis-Hastings chains via shared-randomness Poisson Monte Carlo improves coalescence rates and reduces meeting times up to 50%.

Truong Buu Phan, Gergely Flamich, Ashish Khisti, Shahab Asoodeh

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

Diffusion Path Samplers via Sequential Monte Carlo

Diffusion-based samplers use sequential Monte Carlo along diffusion paths to estimate scores and densities, with control variates reducing variance across OU, interpolant, and annealed paths.

James Matthew Young, Paula Cordero-Encinar, Sebastian Reich, Andrew Duncan and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models

NeuroRVQ uses multi-scale temporal convolutions and hierarchical RVQ codebooks with a phase-aware loss to tokenize biosignals at high fidelity across modalities. NeuroRVQ-FM foundation models using these tokenizers achieve competitive or superior downstream performance, showing that high-fidelity to

Konstantinos Barmpas, Na Lee, Dimitrios Chalatsis, William Raftery and 6 more

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

SynBench: A Benchmark for Differentially Private Text Generation

SynBench benchmarks differentially private text generators across standardized datasets, revealing quality drops on out-of-distribution private data and invalidated privacy guarantees from pre-training contamination.

Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar, Iqra Zahid and 8 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Improving Function Space Flow Matching with Kernel Optimal Transport

kFFM replaces arbitrary pairing in Functional Flow Matching with kernel optimal transport to improve infinite-dimensional generative modeling and outperforms baselines on time-series and PDE benchmarks.

Fred Xu, Thomas Markovich, Barbora Barancikova, Yizhou Sun

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

Neurosymbolic Learning for Inference-Time Argumentation

ITA is a neurosymbolic framework that trains LLMs to generate scored arguments for ternary claim verification, yielding predictions faithfully computed from explicit argument structures.

Gabriel Freedman, Adam Dejl, Adam Gould, Mansi - and 3 more

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

Efficient bias mitigation in T2I diffusion models using Concept Graphs

CO-ALIGN reduces text-to-image diffusion bias via concept-graph alignment across encoders and denoisers, cutting incoherent outputs by 88% while improving fairness and fidelity.

Mansi -, Avinash Kori, Francesco Leofante

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

MyoChallenge 2025: A New Benchmark for Human Athletic Intelligence

MyoChallenge 2025 benchmarks musculoskeletal sports control via simulated table tennis and soccer tasks, advancing agile motor algorithms across 70 teams.

Cheryl Wang, Chun Kwang Tan, Balint Hodossy, Shirui Lyu and 20 more

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

Instance-Optimal Estimation with Multiple LLM Judges on a Budget

EST-IVWE adaptively allocates a budget across judges and instances via biased variance estimates to achieve instance-optimal score estimation, with matching local minimax lower bounds.

Junghyun Lee, Sanghwa Kim, Yassir Jedra, Alexandre Proutiere and 1 more

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

Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers

Training a linear FFN in mean-field transformers drives token distributions to escape attention-induced clustering near final layers.

Noboru Isobe, Daisuke Inoue, Masaaki Imaizumi

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

Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons

A parameter-efficient plugin extends frozen 10-second ECG foundation models to long, variable-length recordings via compatible long-sequence processing and semantically informed temporal modeling, outperforming sliding-window and pooling baselines.

Wei Tang, Jinpei Han, Kangning Cui, Mattia Carletti and 9 more

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

Geometry-Constrained Kolmogorov–Arnold Networks: Learning Edge Geometry via Banach Duality

Geometry-constrained KANs learn per-edge Banach exponents via duality to adapt function-space geometry, matching fixed-basis baselines on symbolic regression while improving noise robustness and small-sample accuracy.

Senanayak Sesh Kumar Karri

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Overcoming Rank Collapse in Feedback Alignment

Feedback Alignment suffers rank collapse in deep networks, so orthogonal optimizers and activation normalization boost accuracy by up to 9 points by increasing effective gradient dimensionality.

Gauthier Boeshertz, Razvan Pascanu, Claudia Clopath

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems

A flow-based estimator enables exact likelihood optimization for recurrent switching dynamical systems, proving broad identifiability and improving disentanglement and forecasting over VAE methods.

Carles Balsells Rodas, Zhengrui Xiang, Francisco Sumba Toral, Yingzhen Li

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks

RRD refines rubrics via recursive decomposition and filtering to improve LLM judge accuracy and reinforcement training rewards on open-ended tasks.

William Shen, Xinchi Qiu, Chenxi Whitehouse, Lisa Alazraki and 5 more

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

MedMisBench: Measuring Epistemic Resilience of LLMs Under Misleading Medical Context

MedMisBench reveals LLM medical accuracy collapses from 71% to 38% under misleading context, exposing a critical evaluation blind spot around epistemic resilience.

Hongjian Zhou, Xinyu Zou, Jinge Wu, Sean Wu and 18 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission

ComprExIT fixes structural bottlenecks in LLM context compression via explicit cross-layer feature selection and coordinated transport, improving F1 up to 18.5% with minimal parameters and 2x faster compression.

Jiangnan Ye, Hanqi Yan, Zhenyi Shen, Heng Chang and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 16 on Hugging Face · Code ★ 10

Structured Coupling for Flow Matching

SCFM augments flow matching with structured latent variables and a shared recognition network to jointly learn structured priors and continuous transport maps, enabling unsupervised clustering and disentanglement without sacrificing generative quality.

Francisco Sumba Toral, Carles Balsells Rodas, Yingzhen Li

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

HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement

HOMIE unifies inter- and intra-subject video personalization via multimodal guidance and reference embeddings, achieving state-of-the-art human-object interaction fidelity.

Yiyang Cai, Nan Chen, Rongchang Xie, Junwen Pan and 7 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 54 on Hugging Face · Code ★ 177

OpenMHC: Accelerating the Science of Wearable Foundation Models

OpenMHC releases the largest open wearable health dataset with open-source foundation models and a unified benchmark across prediction, imputation, and forecasting tasks.

Narayan Schütz, Yuze Bai, Lianggang Pan, Edgar Eggert and 15 more

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

Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces

Task-induced Riemannian metrics define ViT feature geometry via decoder Jacobians, and a learnable low-rank approximation enables accurate geometric token pruning without fine-tuning.

Andrew Bond, Ege E Özlü, Tuna Çimen, Ilkin U Melanlioglu and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting

Flexible discounting in distributional reinforcement learning captures expressive temporal and risk preferences, fixing existing multi-horizon optimality issues.

Mehrdad Moghimi, Anthony Coache, Hyejin Ku

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

Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning

AdaViG uses internal generation-intent and visual-fidelity signals to abort unhelpful visual reasoning steps early, improving multimodal reasoning accuracy by up to 5.7% while cutting visual generation costs by 25-91%.

Wenxi Gao, Guanxi Lu, Didi Zhu, Hao Chen and 4 more

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

Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs

Finetuning LLMs on narrow, benign datasets causes broad ideological shifts across unrelated domains while preserving capabilities, with finetuning amplifying shifts beyond few-shot prompting to extreme outputs.

Robert Graham, Edward Stevinson, Yariv Barsheshat

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

GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models

GDSD improves diffusion language models via advantage-guided denoiser self-distillation that bypasses ELBO likelihood surrogates, boosting test accuracy up to 19.6%.

Xiaohang Tang, Keyue Jiang, Che Liu, Zhao and 3 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026 · ▲ 4 on Hugging Face · Code ★ 22

Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weights

AB-SID-iVAR actively learns Gaussian process targets under unknown self-induced Boltzmann weights, achieving vanishing terminal prediction error without partition function estimation.

Jixiang Qing, Henry Moss, Matthias Sachs

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

Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models

Amortized structured stochastic variational inference couples GP inducing points with latent variables in GPLVMs, improving manifold reconstruction and uncertainty estimation.

Maksym Tretiakov, Sarah Filippi, Vincent Fortuin, Ruth Misener and 2 more

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

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

Embodied-R1.5 is an 8B-parameter embodied foundation model achieving state-of-the-art results on 16 of 24 embodied VLM benchmarks via multi-task balanced RL and a closed-loop planner-grounder-corrector framework.

Yifu Yuan, Yaoting Huang, Xianze Yao, Shuoheng Zhang and 19 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 59 on Hugging Face · Code ★ 60