YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality

YuE2 unifies symbolic and audio music generation through symbolic planning, producing readable scores and full-song audio that outperform public baselines and rival proprietary generators.

Ruibin Yuan, Jiahao Pan, Junyan Jiang, Zhiyue Wu and 31 more

Published Sep 27, 2026 · 0 citations · ▲ 246 on Hugging Face · Code ★ 10,927

Directional Noise Conditioning for Diffusion Models

Mahdi Shafiei, Azade Farshad, Nassir Navab, Yousef Yeganeh

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

Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases

Arsenii Mustafin, Xinyi Sheng, Dominik Baumann

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

CausalAffect: Causally Guided Learning of Psychology-Aligned Facial Affect Relations

Guanyu Hu, Tangzheng Lian, Dimitrios Kollias, Oya Celiktutan and 1 more

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

Approximation Guarantees for Robust Aggregation in Federated Learning

Mélanie Cambus, Darya Melnyk, Tijana Milentijević, Stefan Schmid

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

A method to automatically discover symbolic local learning rules

Andrea Perin, Fabio Anselmi, Stephane Deny

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

Filter Banks: from Low-Rank Representations to Deep Models for Efficient Time Series Forecasting

Ashutosh Vaishnav, Mohsen Amidzadeh, Teemu Kämäräinen, Matti Siekkinen and 1 more

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

Constrained Look-ahead Guidance for Interference-Aware Flow Editing

Doudou ZHANG, Qi CHEN

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

FairMT: Fairness for Heterogeneous Multi-Task Learning

FairMT introduces a unified fairness framework for heterogeneous multi-task learning with partial labels, using asymmetric constraint aggregation and head-aware optimization to improve fairness without sacrificing utility.

Guanyu Hu, Tangzheng Lian, Na Yan, Dimitrios Kollias and 4 more

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

Point Tracking Improves World Action Models

JOPAT predicts tracks and pixels via diffusion transformers to learn dynamics robust to occlusion and appearance variation, improving long-horizon robot policy performance.

Jiarui Guan, Wenshuai Zhao, Yue Pei, Ziliang Chen and 2 more

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

Flexible Flows for Biological Sequence Design

Flexible Flows for Biological Sequence Design proposes structured couplings and latent edit-based rate parameterization to achieve state-of-the-art results across diverse biological sequence generation tasks.

Yogesh Verma, Dani Korpela, Harri Lähdesmäki, Vikas Garg

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

Amortized Bayesian Experimental Design with In-Context Knowledge Conditioning

IMBUE enables amortized Bayesian experimental design to incorporate external deployment knowledge via in-context tokens and a reliability filter, accelerating early information gain with reliable inputs while maintaining baseline performance otherwise.

Zhanghu Zhao, Daolang Huang, Xinyi Wen, Samuel Kaski

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

Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning

Enforcing multi-step latent predictions improves context-based offline meta-RL by capturing task dynamics, reducing value errors, and boosting zero-shot and few-shot generalization.

Mohammadreza Nakhaeinezhad, Aidan Scannell, Kevin Luck, Joni Pajarinen

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

Why Cross-Skeleton Retargeting Is Non-Identifiable: Structural Limits of Generative Motion Models

Cross-skeleton retargeting is structurally non-identifiable: unpaired training yields gauge ambiguity and paired training collapses to conditional means, so source fidelity requires new diagnostics and objectives.

Zhiyuan Li, Wenyan Yang, Pekka Marttinen, Joni Pajarinen

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

Conservative neural posterior estimation via distributionally robust training

DRO-NPE trains neural posterior estimators with distributionally robust worst-case losses to reduce overconfidence and improve calibration under limited simulation budgets.

William Laplante, Yuga Hikida, Charita Dellaporta, Francois-Xavier Briol and 1 more

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

From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows

Fixed-path attribution uniquely requires Aumann-Shapley line integrals, while transport-geodesic paths via minimized kinetic action yield more stable, structured explanations.

Cenwei Zhang, Lin Zhu, Manxi Lin, Lei You

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

Prediction-Powered Active Testing

PPAT combines unbiased LURE estimation with prediction-powered control variates and adaptive acquisition to reduce label variance, yielding valid confidence intervals with fewer labels.

Kianoosh Ashouritaklimi, Valentin Kilian, Daolang Huang, Thomas Rainforth and 1 more

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

Sparsely Supervised Diffusion

Sparsely supervised diffusion masks up to 98% of training pixels to fix spatial inconsistency, improve FID, reduce memorization, and stabilize small-dataset training.

Wenshuai Zhao, Zhiyuan Li, Yi Zhao, Mohammad Vali and 4 more

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

In-Context Black-Box Optimization with Unreliable Feedback

FICBO pretrains a feedback-aware transformer to condition on both optimization history and unreliable auxiliary feedback, estimating source reliability in context to improve black-box query selection.

Nicolas Samuel Blumer, Julien Martinelli, Samuel Kaski

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