Benchmarking Graph Self-Supervised Learning for Node-Level Tasks: Insights and Strong Baseline

Dmitry Eremeev, Gleb Bazhenov, Oleg Platonov, Artem Babenko and 1 more

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

Ensemble Distributionally Robust Bayesian Optimisation

Tigran Ramazyan, Denis Derkach

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

Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective

Dmitry Osin, Egor Surkov, Petr Mokrov, Igor Udovichenko and 4 more

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

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

DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing

DifFRACT extends transcoder-based circuit tracing to multimodal diffusion transformers, yielding exact feature attribution, interpretable circuits for attribute binding and cross-stream propagation, and precise circuit-guided interventions outperforming standard SAE steering.

Artyom Mazur, Nina Konovalova, Aibek Alanov

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

gfnx: Fast and Scalable Library for Generative Flow Networks in JAX

gfnx is a JAX library for training and evaluating GFlowNets that achieves up to 80x speedups over PyTorch benchmarks across diverse tasks.

Daniil Tiapkin, Artem Agarkov, Nikita Morozov, Ian Maksimov and 3 more

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

Tensorion: A Tensor-Aware Generalization of the Muon Optimizer

Tensorion generalizes Muon to tensors via a tractable spectral-norm linear minimization oracle over unfolding matrices, recovering Muon for matrices and improving convergence over Adam on vision tasks.

Vladimir Bogachev, Vladimir Aletov, Alexander Molozhavenko, Sergei Kudriashov and 1 more

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

Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modeling

New metropolis-scale road network datasets with real connectivity and 5-minute speed and volume data expose scalability limits in traffic forecasting and motivate a simple efficient baseline.

Fedor Velikonivtsev, Oleg Platonov, Ekaterina Alimaskina, Gleb Bazhenov and 1 more

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