Pre-ICML 2026 Fest

Join us for the ELLIS Pre-ICML 2026 Fest, a tradition among the Unit Vienna ELLIS community and a fantastic opportunity for researchers with accepted papers at ICML to present their work within the ELLIS Unit Vienna before attending the conference.

The following posters will be presented:

• “Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control” – Fabian Kresse
• “WUSH: Near-Optimal Adaptive Transforms for LLM Quantization” – Jiale Chen
• Diyuan Wu
• “Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning” – Filip Kovačević
• “Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions” – Hossein Zakerinia
• “Towards a holistic understanding of Selection Bias for Causal Effect Identification” – Yiwen Qiu

The event is open to all the ELLIS community for an engaging afternoon of posters, conversations, and networking!

We warmly thank everyone who decided to active participating by presenting their work!