Large-scale analysis of AlphaFold structures reveals organism-specific physicochemical signatures

Large-scale AlphaFold structure analysis reveals organism-specific physicochemical signatures reconstructed via DE-STRESS metrics across 48 proteomes and PDB structures.

Michael J. Stam

Published Oct 4, 2026 · 0 citations

HyperMARL: Adaptive Hypernetworks for Multi-Agent RL

HyperMARL uses agent-conditioned hypernetworks to generate agent-specific parameters that decouple gradients, reducing variance and preserving behavioral diversity across multi-agent benchmarks without added complexity.

Kale-ab Tessera, Arrasy Rahman, Amos Storkey, Stefano Albrecht

Published 2025 · 0 citations

Aligning Few-Step Generative Model via Amortizing Sample-Based Variational Inference

Jaewoo Lee, Hyeongyu Kang, Dohyun Kim, Kyuil Sim and 8 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 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

Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance

Kai Yao

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

Dancing in Fetters: Pareto-Optimal On-Device LLMs under Hardware Constraints

Luoyang Sun, Jiwen Jiang, Yifeng Ding, Fengfa Li and 8 more

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

They Can See It but not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification

MENGYU WANG, Ken Deng, Yftah Ziser, Shay Cohen and 1 more

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

Evaluating Spatiotemporal Reasoning of Vision-Language Models in Atari Gameplay

Mingjia Huo, Yao Fu, Bo Chang, Yaqing Wang and 7 more

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

Where to Approximate in Neurosymbolic Inference?

Samy Badreddine, Emile van Krieken, Luciano Serafini, Antonio Vergari

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

Gradient-based Graph Structure Optimisation for Research Networks

Louis Mahon, Mirella Lapata

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

Do Composed Image Retrieval Benchmarks Require Multimodal Composition?

Matteo Attimonelli, Alessandro De Bellis, Aryo Gema, Rohit Saxena and 7 more

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

How deep is your network? Deep vs. shallow learning of transfer operators

Mohammad Tabish, Benedict Leimkuhler, Stefan Klus

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

CRISP: Compositional Reasoning over Images via Stackable Programs for VLMs

Arnas Uselis, Yujin Jeong, Yanpeng Zhao, Alexander Rubinstein and 3 more

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

Git Context Controller: Manage the Context of Agents by Agentic Git

Junde Wu, Minhao Hu, Jiayuan Zhu, Shengda Zhu and 5 more

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

GPT-Image-Edit-1M: An Auditable Million-Scale Dataset for Instruction-Guided Image Editing

Yuhan Wang, Siwei Yang, Bingchen Zhao, Letian Zhang and 7 more

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

Local Policy Manifolds for Efficient Multi-Objective Reinforcement Learning

Qiyue Xia, Tianwei Wang, J. Michael Herrmann

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

Constrained Graph Clustering: A Spectral Algorithm with Generalized Eigenvectors

Shihong Song, He Sun

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

PPO in the Fisher-Rao geometry

FR-PPO leverages Fisher-Rao geometry to provide monotonic policy improvement guarantees and sub-linear convergence without dependence on state or action space dimensions.

Razvan-Andrei Lascu, David Siska, Lukasz Szpruch

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

Even More Guarantees for Variational Inference in the Presence of Symmetries

Symmetric targets let misspecified variational inference recover exact means and correlations via KL or α-divergences without log-concavity assumptions.

Lena Zellinger, Antonio Vergari

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

Benchmarking Open-Ended Multi-Agent Coordination in Language Agents

Alem benchmarks open-ended multi-agent coordination for language agents, showing frontier LLMs average ~6% returns and individual competence does not imply coordination competence.

Kale-ab Tessera, Andras Szecsenyi, Cameron Barker, Alexander Rutherford and 6 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 7 on Hugging Face · Code ★ 51

Mirror Descent-Ascent for mean-field min-max problems

Mirror descent-ascent achieves O(N^{-1/2}) and O(N^{-2/3}) convergence to mean-field Nash equilibria via infinite-dimensional dual Bregman analysis.

Razvan-Andrei Lascu, Mateusz Majka, Lukasz Szpruch

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

SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks

SCOPE co-evolves a task-generating challenger and retrieval solver with rubric-based self-judging to improve open-ended and QA performance without curated data.

Wai-Chung Kwan, Aryo Gema, Joshua O Leang, Pasquale Minervini

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 25 on Hugging Face · Code ★ 2

Approximate Envy-Free Allocations up to any k Goods

For any k>2, (k+1)/(k+2)-EFkX allocations always exist and are computable in polynomial time, yielding 3/4-EF2X for any number of agents and 2/3-EF X for eight agents.

Aris Filos-Ratsikas, Georgios Kalantzis, Fangxiao Wang

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

Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels

Classifier-based adaptive stopping treats MCMC trajectory termination as learnable via GFlowNets, reducing trajectory lengths while improving mode coverage and mixing.

Kirill Korolev, Nikita Morozov, Stepan Pavlenko, Esmeralda S Whitammer and 1 more

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

Hyperagents

Hyperagents integrate editable task and meta agents to enable metacognitive self-modification, with DGM-H improving across domains and accumulating meta-level improvements.

Jenny Zhang, Bingchen Zhao, Wannan Yang, Jakob Foerster and 4 more

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

Autonomous Scientific Discovery via Iterative Meta-Reflection

DiscoPER autonomously discovers scientific patterns via iterative meta-reflection and statistical testing, recovering 8 of 9 ecological patterns and outperforming baselines.

Bingchen Zhao, Sara Beery, Oisin Mac Aodha

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

Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences

Spatiotemporal Noise-Contrastive Estimation learns energy-based models via joint spatiotemporal differences to avoid failure modes of spatial or temporal methods alone, matching state-of-the-art density estimation.

Hanlin Yu, RuiKang OuYang, Partha Kaushik, Arto Klami and 2 more

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

Self-Improving World Modelling with Latent Actions

SWIRL learns world models from state-only sequences via latent actions and alternating forward/inverse dynamics, improving LLM/VLM reasoning benchmarks by up to 28%.

Yifu QIU, Zheng Zhao, Waylon Li, Yftah Ziser and 3 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 32 on Hugging Face · Code ★ 20

FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators

FARE detects bait-and-switch swaps of certified AI image generators at deployment by estimating forensic acceptance regions via hard-sample training, outperforming baselines at strict thresholds.

Kai Yao, Marc Juarez

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

Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs

DES selects sequence-level expert coresets for diffusion MoE LLMs to cut unique activations over 55% and latency up to 38% while retaining 99% accuracy, decoupling memory from parallelism.

Hao Chen, Zhiwen Mo, Royson Lee, Qianzhou Wang and 5 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 1 on Hugging Face

Imperfect World Models are Exploitable

A novel definition of model exploitation reveals it is essentially unavoidable for large policy sets and cannot be precluded in finite ones, yielding safe planning limits.

Logan M Bhamidipaty, Esmeralda S Whitammer, David Abel, Mykel J Kochenderfer and 1 more

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

Interpreting Latent Protein Language Model Features with Geometric Annotations

Sparse autoencoders in ESM-2 are interpreted via Cα geometric features, revealing localized structural patterns and substructure within biological labels that sequence annotations miss.

Siddharth Setlur, Djordje Mihajlovic, Darrick Lee

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Probing Visual Planning in Image Editing Models

EAR reformulates visual planning as single-step editing and evaluates it on abstract maze puzzles, showing models fail zero-shot but generalize via finetuning yet remain below human efficiency.

Zhimu Zhou, Yanpeng Zhao, Qiuyu Liao, Bo Zhao 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 · Code ★ 1

Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence

Policy mirror descent with inexact TD actor-critic converges for entropy-regularized MDPs in general spaces, with sublinear or linear rates under sufficient TD steps.

Denis Zorba, David Siska, Lukasz Szpruch

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