Instant Personalized Large Language Model Adaptation via Hypernetwork

A hypernetwork enables instant personalized large language model adaptation by generating user-specific parameters directly from user data.

Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen, Zheng Li and 7 more

Published 2026 · 1 citation

Emotion-Trained Vision Models Do Not Necessarily Learn EEG-Aligned Facial Dynamics

Maryem Benslimane, Hamza Abdelhedi, Vanessa Hadid, Karim Jerbi

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

RobustGenBench: A Benchmark for Robust Generalization to Adversarial and Common Perturbations, with Applications to Vision and Vision-Enabled Large Language Models

Maxime Heuillet, JONAS NGNAWE, Yann Pequignot, Rishika Bhagwatkar and 5 more

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

From Claims to Context: Holistic Information Verification Requires Contextual Signals

Emma Kondrup, Islam Eldifrawi, Tong Wu, Zachary Yang and 5 more

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

Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization

Bidirectional Information Flow enables continuous two-way communication in hierarchical Gaussian processes for Bayesian optimization, improving sample efficiency, training robustness, and modular subtask reuse while significantly outperforming unidirectional and vanilla methods.

Juan D. Guerra, Thomas Garbay, Numa Dancause, Guillaume Lajoie and 1 more

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

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning

LLM-based cellular perturbation reasoning relies on intrinsic gene tendencies rather than true perturbation effects, and contrastive evidence organization improves prediction accuracy substantially.

XINYU YUAN, Xixian Liu, Jianan Zhao, Ya Shi Zhang and 2 more

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

Agentick: A Unified Benchmark for General Sequential Decision-Making Agents

Agentick unifies RL and foundation model agent evaluation across 37 tasks, finding no dominant approach and substantial room for improvement.

Roger Creus Castanyer, Pablo Samuel Castro, Glen Berseth

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

Phases of Muon: When Muon Eclipses SignSGD

Spectral optimizer analysis reveals three phases where Muon's SignSVD preconditions covariance differently than SignSGD.

Elliot Paquette, Noah Marshall, Lucas Benigni, Guangyuan Wang and 2 more

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

GeneZip: Region-Aware Compression for Long Context DNA Modeling

GeneZip uses region-aware compression to achieve high base-pairs-per-token ratios, improves DNA modeling benchmarks, and enables 128K-context training on limited hardware.

Jianan Zhao, Xixian Liu, Zhihao Zhan, XINYU YUAN and 2 more

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

One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective

Treating neural quantum state optimization as advantage policy-gradient enables PWO, a trust-region algorithm that improves stability and scales to 1.5B parameters.

Juan A Duque, Sergio García Heredia, Vinicius Hernandes, Eliska Greplova and 3 more

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