Upcoming Events & Talks

Today 05-03-2026 Talk Deep Models and Optimization

„From Growing to Looping: Inducing Iterative Computation for Reasoning“

by Ferdinand Kapl

Abstract: Deep Transformers are costly to train and often underuse their later layers, a failure mode known as the Curse of Depth. Depth growth, which trains models from shallow to deep by duplicating layers, not only reduces training cost but also is associated with stronger reasoning performance. Layer-wise analyses suggest that growth encourages more effective use of depth, reshapes how information is processed across layers, and facilitates the emergence of permutable computational blocks. Building on these mechanistic signatures, a connection emerges to looping, where a block of layers is reused across depth: looped and depth-grown models exhibit convergent depth-wise patterns consistent with a shared form of iterative computation. This connection is both composable and practical: ... Antonio Orvieto

---

Today 05-03-2026 Max Planck Lecture Registration

Toward Intelligent Metamaterial Machines

Max Planck Lecture, given by Katia Bertoldi

The Max Planck Institute for Intelligent Systems is delighted to invite you to its 2026 Max Planck Lecture. This year, we are excited to welcome Katia Bertoldi, Professor of Applied Mechanics, Harvard University, as our guest speaker. Christoph Keplinger Katherine J. Kuchenbecker Barbara Kettemann Eva Lämmerhirt

---

06-03-2026 Workshop

4th Workshop of Tübingen Women in Machine Learning

From Benchmarks to Brains: Incentives and Responsibility in Modern AI

We are happy to invite you to the 4th workshop of Tübingen Women in Machine Learning. The program will include invited talks, interactive sessions, a poster session, and opportunities for discussion and networking.

---

06-03-2026 PhD Thesis Defense Haptic Intelligence

Haptify: A Measurement-Based System for Quantifying the Quality of Haptic Interfaces

Grounded force-feedback (GFF) devices, exoskeletons, and other haptic robots modulate human movement through carefully engineered mechanical, electrical, and computational designs. Given their significant societal potential and often high cost, it is essential to fairly and efficiently assess the quality of these intimate cyber-physical interfaces. However, existing device specifications and low-level performance metrics often fail to capture the nuanced qualities that expert users perceive during hands-on experimentation. To address this gap, this thesis introduces Haptify, a comprehensive benchmarking system that can thoroughly, fairly, and noninvasively evaluate GFF haptic devices. Haptify integrates multiple sensing modalities - a seven-camera optical motion-capture system, a cus... Katherine J. Kuchenbecker Farimah Fazlollahi

---

06-03-2026 PhD Thesis Defense Haptic Intelligence Dynamic Locomotion

The Human Leg Catapult: Biological Mechanisms for Walking Gait Replicated in the EcoWalker Robot

Humanoid robots and assistive devices have yet to match the efficiency and adaptability of able-bodied human walking in challenging environments. To bridge this performance gap, my projects explored the underlying mechanisms of human locomotion, focusing on the ankle push-off. Ankle push-off has a prominent role in walking due to its high-power output at the end of the stance phase, and due to the impact of its timing on the adaptability to diverse environments. The human leg catapult analogy provides a framework for the projects to understand and replicate the complex biological mechanisms that govern human walking gait. As a platform for the replication, the human-like bipedal EcoWalker robot was developed from version 1 to 3 in three consecutive projects, with iterative design and co... Katherine J. Kuchenbecker Alexander Badri-Spröwitz Bernadett Kiss

---

19-03-2026 Talk Wild, Efficient, and Innovative AI

Talk « Brain-inspired sparse network science for next generation efficient and sustainable AI »

By Prof. Carlo Vittorio Cannistraci

Artificial neural networks (ANNs) are foundational to contemporary artificial intelligence (AI), however their conventional fully connected architectures are computationally inefficient. Contemporary large language models consume vast amounts of power at rates over 100 times that of the human brain. In stark contrast, the brain's inherently sparse connectivity facilitates exceptional capabilities with minimal expenditure: learning with just a few watts. Brain-inspired network science research can play a relevant role in designing low-consumption and efficient deep learning. We need to develop concepts and theories for an ecological and sustainable approach to AI. Some of these new computing paradigms can be inspired from the physics of the brain network architecture and its complex ... Shiwei Liu

---

23-03-2026 - 26-03-2026 Conference

CPAL - Conference for Parsimony and Learning

The Conference on Parsimony and Learning (CPAL) is an annual research conference focused on addressing the parsimonious, low dimensional structures that prevail in machine learning, signal processing, optimization, and beyond. We are interested in theories, algorithms, applications, hardware and systems, as well as scientific foundations for learning with parsimony.

---

23-04-2026 Event

Girls' Day 2026

Erlebt einen spannende Tag voller Entdeckungen am Max-Planck-Institut für Festkörperforschung und am Max-Planck-Institut für Intelligente Systeme in Stuttgart beim Girls' Day am 23. April 2026! Barbara Kettemann Linda Behringer

---

23-04-2026 Conference

IntCDC Spring Conference 2026

The IntCDC Spring Conference 2026 will take place on 23 April 2026 at the Max Planck Institute for Intelligent Systems in Stuttgart.

---