Cross-Question Reliable Reinforcement Learning

Hector G. Rodriguez, Marcus Rohrbach

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

Decomposing Effects in Neural Causal Models

Matej Zečević, Devendra Singh Dhami, Kristian Kersting

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

A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning

Anish Abhijit Diwan, Jan Peters, Oleg Arenz

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

JAXtari: High-Throughput and Easy-to-Modify Arcade Learning Environment

Quentin Delfosse, Raban Emunds, Paul Seitz, Sebastian Wette and 4 more

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

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?

Nils Grandien, David Steinmann, Felix Friedrich, Kristian Kersting

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

xWhy: Causal Learning from Explanations

Nicholas Tagliapietra, Florian Peter Busch, Moritz Willig, Matej Zečević and 3 more

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

SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring

SIEVES improves selective prediction for visual question answering by scoring visual evidence quality, boosting out-of-distribution coverage up to three times across open and closed models without requiring internal weights.

Hector G. Rodriguez, Marcus Rohrbach

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

Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction

ZendoWorld evaluates AI agents on active visual rule induction and finds high prediction accuracy does not imply rule recovery, with VLM agents proposing near-uninformative experiments.

Sophia Koehler, Antonia Wüst, Inga Ibs, Top Piriyakulkij and 4 more

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

Generative Scenario Rollouts for End-to-End Autonomous Driving

GeRo enables vision-language-action models to generate language-grounded future traffic scenes via autoregressive rollouts, improving Bench2Drive driving scores by 15.7 and success rates by 26.2.

Rajeev Yasarla, Deepti Hegde, Shizhong Han, Hsin-Pai Cheng and 10 more

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

Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves

Depth-recurrent attention mixtures (Dreamer) combine sequence, depth, and sparse expert attention to scale latent reasoning efficiently, requiring 2, 8x fewer training tokens than matched baselines while improving expert diversity.

Jonas Knupp, Jan Metzen, Jeremias Bohn, Georg Groh and 1 more

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

Nautilus: From One Prompt to Plug-and-Play Robot Learning

NAUTILUS converts a single prompt into robot learning workflows via plug-and-play agent skills, typed contracts, and automated validation, reducing cross-family engineering overhead.

Yufeng Jin, Jianfei Guo, Xiaogang Jia, Yu Deng and 7 more

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