Decomposing Earth Embeddings with Sparse Autoencoders

Vitus Benson, Fanny Yang, Markus Reichstein

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

Forgetting to Improve: Principled Data Removal in Active Learning

Manuel Wendl, Erik Englesson, Andreas Krause, Carl Henrik Ek

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

Joint protein, mRNA, DNA sequence design and optimization with nucleotide-level Potts models

Blazej Banaszewski, Lars J Dornfeld, Dexiong Chen, Karsten Borgwardt and 1 more

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

CryptanalysisBench: Can LLMs do cryptanalysis?

Lukas Fluri, Avital Shafran, Nicholas Carlini, Matthew Jagielski and 4 more

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

SuperSycophantic: Stress-Testing Frontier LLMs from Single- to Multi-Turn Sycophancy

Terry J Zhang, Oscar S Yasunaga, Wenyuan Jiang, Jessica Bo and 7 more

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

Channel Mixer: A Pretrainable Tokenizer for Scalable Multi-Channel Vision Transformers

Lukas Miklautz, Lucas Miranda, Nikola Bulat, Armin Lambacher and 2 more

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

Speculative Self-Distillation enables Efficient Knowledge Internalization

Shayan Talaei, Agam Bhatia, Arshia Soltani Moakhar, Jonas Hübotter and 2 more

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

DexOPE: 6D Object Pose Estimation in Dexterous Manipulation

Ke Wu, Zhiwei Yang, Xiangting Meng, Zicheng Zhang and 4 more

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

From Contexts to Conditionals: Statistical Self-Consistency of Persona Prompting

Patrik Wolf, Thomas Kleine Buening, Andreas Krause, Celestine Mendler-Dünner

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

Certifiably Optimal Robust Angular Synchronization

Daniel Barath, Keisuke Tateno, Marc Pollefeys, Federico Tombari

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

Who Called? V33DA: A Physically Verified Multimodal Benchmark for Vocal Attribution in Zebra Finch Groups

Maris Basha, Yuhang Wang, Xiaoran Chen, Longbiao Cheng and 4 more

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

Parasite Features: Causal Abstraction Through Spurious Pathways

Denis Sutter, Qing Yao, Sasha Boguraev, Julian Minder and 4 more

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

Phase Transitions in Heavy-Tailed Mean Estimation under $\ell_p$ Norms

Ishaq Aden-Ali, Yeshwanth Cherapanamjeri, Mikael Møller Høgsgaard, Kasper Green Larsen and 1 more

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

Forecasting Microbial Dynamics: Evaluation Protocol and Prior-Spectrum Benchmark

Fedor Sergeev, Anna Győrffy-Kerekes, Tristan Gollmart, Vincent Fortuin and 2 more

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

Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Sciences

Levi Lingsch, Georgios Kissas, Johannes Jakubik, Siddhartha Mishra

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

A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale

Dongxu Wei, QiXu, Zhiqi Li, Hangning Zhou and 5 more

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

Federated Logic Gate Networks via Boolean Feature Selection

Felix Kunze, Antonio Di Maio

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

Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study

Hao Dong, Hongzhao Li, Shupan Li, Muhammad Haris Khan and 2 more

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

Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators

Heejin Do, Shashank Sonkar, Mrinmaya Sachan

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

Treat Domain-Specific Languages as Design Variables in LLM Agents

Letian Li, Wenyuan Jiang, Xin Yang, Shuzhao Xie and 4 more

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

Fixed-Point Reasoning: Stable and Adaptive Deep Looped Models

Sajad Movahedi, Shlomo Libo Feigin, Vera Milovanović, Alexander Theus and 4 more

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

DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving

Zixuan Chen, Wenyuan Jiang, Junling Wang, Mrinmaya Sachan and 1 more

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

Long-Rollout Stability in AI Weather Models: A Quantitative Benchmark and Analysis

Fanny Lehmann, Firat Ozdemir, Yun Cheng, Torsten Hoefler and 3 more

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

GeoDial: A Multimodal Dialog Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns

Sankalan Pal Chowdhury, Junling Wang, Donya Rooein, April Wang and 1 more

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

When Does Non-Uniform Replay Matter in Reinforcement Learning?

Michal Korniak, Mikołaj Czarnecki, Yarden As, Piotr Miłoś and 2 more

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

FraudBench: A Legal Evaluation of AI Deception on Realistic Tasks

Kevin Wei, Sumaya N Adan, Stephan Llerena, Mark L Gitau and 16 more

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

Time-Sensitive Anytime-Valid Testing

A time-sensitive testing-by-betting framework favors early rejection via time-weighted rewards, yielding Bellman-optimal e-processes and an exponential-decay-optimal criterion recovering classical growth-rate optimality at large scales.

Eugenio Clerico, Tobias Wegel, Iskander Azangulov, Patrick Rebeschini

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

Generating in the Limit with Infinitely Many Hallucinations

Language generation in the limit is recast as recall-precision trade-offs, showing that allowing infinitely many vanishing-frequency hallucinations can strictly increase recall when adversaries withhold target portions.

Irene Strauss, Alexandra Butoi, Ryan Cotterell

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

Breaking the Synthesis Barrier for AI-Designed DNA Libraries

PGLD optimizes synthesis-aware stochastic DNA libraries via policy gradients to bypass synthesis cost limits, enabling million-sequence libraries for antibody exploration at low cost.

Scott Sussex, Ema Borevković, Frederieke Lohmann, Ningning Chen and 3 more

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

Scaling Full Conformal Image Classifiers

Targeted Full Conformal Prediction uses vision-language models to prune labels and scale full conformal image classification with stable coverage and modest overhead.

Julio Silva-Rodríguez, Ender Konukoglu

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

Probing Persona-Dependent Preferences in Language Models

Linear probes on LLM residual streams identify a shared preference vector tracking pairwise choices across personas, with cross-persona transfer and causal steering.

Oscar Gilg, Pierre Beckmann, Daniel Paleka, Patrick Butlin

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

LittleLearner: Language Models Under Pedagogically-Controlled Knowledge Exposure

LittleLearner is a 5B-parameter model trained on grade-capped elementary data to study controlled knowledge acquisition and bounded capability growth.

Fanfei Li, Jana Zeller, Manuel Prada-Corral, Thaddäus Wiedemer and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 9 on Hugging Face

Grid Games: The Power Of Multiple Grids for Quantizing Large Language Models

Multiple grids per group improve 4-bit quantization by selecting better grids per group, consistently boosting accuracy over single-grid FP4 for weights and activations.

Vage Egiazarian, Erik Schultheis, Andrei Panferov, Earl Killian and 2 more

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

CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction

CLoSeR detects loop candidates via global descriptors to close loops in streaming reconstruction, reducing drift and producing consistent kilometer-scale geometry with SE(3) pose optimization.

Moyang Li, Zihan Zhu, Wei Zhang, Marc Pollefeys and 1 more

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

GenRec: Knowing Where to Reconstruct and Where to Generate

GenRec separates reconstruction and generation via observation masks to preserve fidelity in visible regions while synthesizing plausible unobserved content.

Ata Çelen, Jaewoo Jung, Federico Tombari, Marc Pollefeys and 3 more

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

Validating Causal Abstraction Metrics on Simulated Complex Systems

Benchmarking thirty metrics on ten simulated complex systems shows only causal metrics reliably validate high-level explanations when testing unmapped-variable faithfulness, leading to the Causal Abstraction Error metric converging with thirty interventions.

Maxime Méloux, Tiago Pimentel, François Portet, Maxime Peyrard

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

Prediction-Intervention Games and Invariant Sets

Prediction-intervention games model leaders choosing predictors against followers intervening on covariates; stable-blanket predictors are provably optimal or near-optimal.

Linus Kühne, Felix Schur, Jonas Peters

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

Divide et Calibra: Multiclass Local Calibration via Vector Quantization

Divide et Calibra uses vector quantization to learn shared, region-specific multiclass calibration maps that improve local calibration without reducing latent dimensions.

Cesare Barbera, Lorenzo Perini, Giovanni De Toni, Andrea Passerini and 1 more

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

Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets

Under local PŁ conditions, unique optimistic lower-level selection ensures hyper-gradient differentiability via pseudoinverses, yielding HG-MS with manifold-dependent convergence and strong LLM reweighting results.

Saeed Masiha, Zebang Shen, Negar Kiyavash, Niao He

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

Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport

Morph is a flexible-size generative model for 3D molecular design that uses unbalanced optimal transport to dynamically adapt molecular size, improving property steering and enabling out-of-distribution generation.

Malte Franke, Stefan P. Schmid, Žarko Ivković, Kjell Jorner and 1 more

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