Events & Talks

Social Foundations of Computation Talk Evimaria Terzi 01-07-2024 Beyond accuracy: understanding the performance of LLMs on exams designed for humans Many recent studies of LLM performance have focused on the ability of LLMs to achieve outcomes comparable to humans on academic and professional exams. However, it is not clear whether such studies shed light on the extent to which models show reasoning ability, and there is controversy about the significance and implications of such results. We seek to look more deeply into the question of how and whether the performance of LLMs on exams designed for humans reflects true aptitude inherent in LLMs. We do so by making use of the tools of psychometrics which are designed to perform meanin... Ana-Andreea Stoica

Social Foundations of Computation Talk Evimaria Terzi 01-07-2024 Beyond accuracy: understanding the performance of LLMs on exams designed for humans Ana-Andreea Stoica

Social Foundations of Computation Talk Nathan Kallus 24-06-2024 The Unreasonable Effectiveness of Distributional Reinforcement Learning Moritz Hardt

Talk Dr. Chaoqun Dong 14-06-2024 Soft Materials and Electronics: Novel Designs and Applications Soft materials assemblies offer a diverse range of sophisticated functions, including sensing and actuation, particularly relevant in intimate interactions with the human body. While hard materials dominate current machine and robot construction, there is a growing recognition of the advantages of soft materials in biomedical devices and human-machine interfaces. Soft systems offer comfort, safety, adaptability, and cost-effectiveness. However, the development of soft devices, encompassing sensors, actuators, and power sources, is in its early stages, requiring further research in materials... Katherine J. Kuchenbecker Christoph Keplinger

Perceiving Systems Talk Shixiang Tang 10-06-2024 Towards Human-Centric Foundation Models: Pretraining Datasets and Unified Architectures Recent years have witnessed great research interests in Human-Centric Visual Computing, such as person re-identification in social surveillance, mesh recovery in Metaverse, and pedestrian detection in autonomous driving. The recent development of large model offers the opportunity to unify these human-centric tasks and achieve improved performance by merging public datasets from different tasks. This talk will present our recent work on developing human-centric unified models on 2D vision, 3D vision, Skelton-based and vision-language tasks. We hope our model will be integrated to the curre... Yandong Wen

Talk Dr.-Ing. Renate Sachse 07-05-2024 Computational Mechanics for Plant-Inspired Soft Robots Soft robotics, an emerging field, focuses on creating flexible and adaptable robots inspired by the pliability found in living organisms. Developed through advancements in materials and manufacturing techniques, soft robots offer unique capabilities such as delicate object manipulation and safe human interaction. In soft robot design, the greatest challenge currently lies in identifying a structure capable of executing a targeted maneuver considering its intricate mechanical behavior. A possible design concept is to learn from biological systems and transfer the functionalities to biomime... Katherine J. Kuchenbecker Christoph Keplinger

Perceiving Systems Talk Shengqu Cai 02-05-2024 Generative Rendering and Beyond Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious manual process, which can be automated by emerging text-to-video diffusion models (SORA). Despite great promise, video diffusion models are difficult to control, hindering users from applying their own creativity rather than amplifying it. In this talk, we present a novel approach called Generative Rendering that combines the controllability of dynamic 3D me... Shrisha Bharadwaj Michael Black

Outreach 25-04-2024 Girls Day at Tübingen MPI-IS Labs instead of schools! Claudia Daefler Nisha Tyagi

Outreach 20-04-2024 Open House Stuttgart 2024 We warmly invite you to the 2024 Open Day on April 20, 2024 from 10 am to 4 pm. This day is jointly hosted by the Max Planck Institute for Intelligent Systems and the Max Planck Institute for Solid State Research on our Stuttgart campus in Büsnau. We are excited to have you visit so you can experience the miraculous power of science up close! Barbara Kettemann Claudia Daefler

Event 11-04-2024 From Idea to Impact - Unlock Your Entrepreneurial Potential (Tübingen) Explore the opportunities to transform your research into a business with our comprehensive incubation. Nisha Tyagi

Event 10-04-2024 From Idea to Impact - Unlock Your Entrepreneurial Potential (Stuttgart) Explore the opportunities to transform your research into a business with our comprehensive incubation. Claudia Daefler

Perceiving Systems Talk Maria Korosteleva 04-04-2024 Modeling and Reconstructing Garments with Sewing Patterns The problems of creating new garments (modeling) or reproducing the existing ones (reconstruction) appear in various fields: from fashion production to digital human modeling for the metaverse. The talk introduces approaches to a novel garment creation paradigm: programming-based parametric sewing pattern construction and its application to generating rich synthetic datasets of garments with sewing patterns. We will then discuss how the availability of ground truth sewing patterns allows posing the learning-based garment reconstruction problem as a sewing pattern recovery. Such reformulatio... Yao Feng Michael Black

Event 22-03-2024 Women in Science We would like to cordially invite you all to a scientific talk and discussion on women in science with Ashley Bourke and Teresa Spanò, two of the authors of the article "A European Perspective on Structural Barriers to Women’s Career Progression in Neuroscience", which was recently published in Nature Neuroscience. Alona Shagan Daniela Macari Carolin Lewis

Robotic Materials Talk Dr. Jianyu Li 18-03-2024 Bioadhesive Technologies with Mechanical Principles Bioadhesive technologies are important in a wide range of applications, spanning from wound management to wearable technologies. Forming and controlling tough adhesion on biological tissues has been a long-lasting challenge, necessitating transdisciplinary approaches. In my talk, I will share our recent progress in the design, mechanics, and applications of tough bioadhesives. I will first discuss the limitations of clinically used surgical glues and blood clots in terms of adhesion properties. I will then present the mechanical principles for making tough bioadhesives that exhibit superior... Christoph Keplinger Adrian Koh

Haptic Intelligence IS Colloquium Dr. Hannah Stuart 18-03-2024 Designing Mobile Robots for Physical Interaction with Sandy Terrains One day, robots will widely support exploration and development of unstructured natural environments. Much of the work I will present in this lecture is supported by NASA and is focused on robot design research relevant to accessing the surfaces of the Moon or Mars. Tensile elements appear repeatedly across the wide array of missions envisioned to support human or robotic exploration and habitation of the Moon. With a single secured tether either rovers or astronauts, or both, could belay down into steep lunar craters for the exploration of permanently shadowed regions; the tether prevents ... Katherine J. Kuchenbecker

Perceiving Systems Talk Qixing Huang 13-03-2024 Geometric Regularizations for 3D Shape Generation Generative models, which map a latent parameter space to instances in an ambient space, enjoy various applications in 3D Vision and related domains. A standard scheme of these models is probabilistic, which aligns the induced ambient distribution of a generative model from a prior distribution of the latent space with the empirical ambient distribution of training instances. While this paradigm has proven to be quite successful on images, its current applications in 3D generation encounter fundamental challenges in the limited training data and generalization behavior. The key difference be... Yuliang Xiu

Symposium 27-02-2024 Scientific Symposium 2024 All current and former employees and partners of the Max Planck Institute for Intelligent Systems are welcome to attend this event. If you have any questions, please contact Eva Lämmerhirt, Institute Management Officer, at eva.laemmerhirt@tuebingen.mpg.de Katherine J. Kuchenbecker Christoph Keplinger Matthias Tröndle Eva Laemmerhirt

Haptic Intelligence PhD Thesis Defense 23-02-2024 Creating a Haptic Empathetic Robot Animal That Feels Touch and Emotion Social touch, such as a hug or a poke on the shoulder, is an essential aspect of everyday interaction. Humans use social touch to gain attention, communicate needs, express emotions, and build social bonds. Despite its importance, touch sensing is very limited in most commercially available robots. By endowing robots with social-touch perception, one can unlock a myriad of new interaction possibilities. In this talk, I will present my work on creating a Haptic Empathetic Robot Animal (HERA), a koala-like robot for children with autism. I will demonstrate the importance of establishing desig... Katherine J. Kuchenbecker Rachael Burns

Social Foundations of Computation Talk Lili Xu 19-02-2024 High-stakes decisions from low-quality data:  AI decision-making for planetary health Ana-Andreea Stoica

Symposium 08-02-2024 IMPRS-IS 2024 Interview Symposium Keynotes All members of the IMPRS-IS community are invited to attend the eighth annual interview symposium taking place from Thursday, February 1, to Friday, February 9, 2024. The event will feature two keynote presentations from IMPRS-IS faculty Dr. Wieland Brendel and Prof. Andreas Bulling. Katherine J. Kuchenbecker Leila Masri Sara Sorce

Haptic Intelligence Talk Marie Großmann 23-01-2024 Constructing Perceptions: A Sociological Perspective on Sensors The sensory perception of the world, including seeing and hearing, tasting and smelling,touching and feeling, are necessary social skills to become a social counterpart. In this context,the construction of a perceptible technology is an intersection where technical artifacts have the capability to interact and sense their environment. Sensors as technical artifacts not only measure various (physical) states, with their presented results influencing perceptions and actions, but they also undergo technical and computational processing. Sensors generate differences by capturing and measuring ... Katherine J. Kuchenbecker

Perceiving Systems Talk Luming Tang 18-01-2024 Mining Visual Knowledge from Large Pre-trained Models Computer vision made huge progress in the past decade with the dominant supervised learning paradigm, that is training large-scale neural networks on each task with ever larger datasets. However, in many cases, scalable data or annotation collection is intractable. In contrast, humans can easily adapt to new vision tasks with very little data or labels. In order to bridge this gap, we found that there actually exists rich visual knowledge in large pre-trained models, i.e., models trained on scalable internet images with either self-supervised or generative objectives. And we proposed differ... Yuliang Xiu Yandong Wen

Haptic Intelligence Talk Dr. Janneke Schwaner 07-12-2023 Biomechanics and Control of Agile Locomotion: from Walking to Jumping Animals seem to effortlessly navigate complex terrain. This is in stark contrast with even the most advanced robot, illustrating that navigating complex terrain is by no means trivial. Humans’ neuromusculoskeletal system is equipped with two key mechanisms that allow us to recover from unexpected perturbations: muscle intrinsic properties and sensory-driven feedback control. We used unique in vivo and in situ approaches to explore how guinea fowl (Numida meleagris) integrate these two mechanisms to maintain robust locomotion. For example, our work showed a modular task-level control of leg ... Katherine J. Kuchenbecker Andrew Schulz

Perceiving Systems Talk Partha Ghosh 30-11-2023 RAVEN: Rethinking Adversarial Video generation with Efficient tri-plane Networks We present a novel unconditional video generative model designed to address long-term spatial and temporal dependencies. To capture these dependencies, our approach incorporates a hybrid explicit-implicit tri-plane representation inspired by 3D-aware generative frameworks developed for three-dimensional object representation and employs a singular latent code to model an entire video sequence. Individual video frames are then synthesized from an intermediate tri-plane representation, which itself is derived from the primary latent code. This novel strategy reduces computational complexity b... Yandong Wen

Event 11-11-2023 Tübingen Science & Innovation Days 2023 / Open House MPI-IS The Max Planck facilities of the Tübingen Max Planck Campus invite interested people of all ages to take a look behind the scenes of basic research. Claudia Daefler Nisha Tyagi

Perceiving Systems Talk Weiyang Liu 19-10-2023 Orthogonal Butterfly: Parameter-Efficient Orthogonal Adaptation of Foundation Models via Butterfly Factorization Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is increasingly important. In this paper, we study a principled finetuning paradigm -- Orthogonal Finetuning (OFT) -- for downstream task adaptation. Despite demonstrating good generalizability, OFT still uses a fairly large number of trainable parameters due to the high dimensionality of orthogonal matrices. To address this, we start by examining OFT from an information transmission perspective, and then identify a ... Yandong Wen

Haptic Intelligence Talk Dr. Diego Ospina 17-10-2023 Project neuroArm: Image-guided Medical Robotics Program Project neuroArm was established in 2002, with the idea of building the world’s first robot for brain surgery and stereotaxy. With the launch (2007) and integration of the neuroArm robot in the neurosurgical operating room (May 2008), the project continues to spawn newer technological innovations, advance tele-robotics through sensors and AI, and intelligent surgical systems towards improving safety of surgery. This talk will provide a high-level overview of two such technologies the team at Project neuroArm is currently developing and deploying: i) neuroArm+HD, a medical-grade sensory imme... Katherine J. Kuchenbecker Rachael Lorsa

Perceiving Systems Talk Zhen Liu 12-10-2023 Ghost on the Shell: An Expressive Representation of General 3D Shapes The creation of photorealistic virtual worlds requires the accurate modeling of 3D surface geometry for a wide range of objects. For this, meshes are appealing since they enable 1) fast physics-based rendering with realistic material and lighting, 2) physical simulation, and 3) are memory-efficient for modern graphics pipelines. Recent work on reconstructing and statistically modeling 3D shape, however, has critiqued meshes as being topologically inflexible. To capture a wide range of object shapes, any 3D representation must be able to model solid, watertight, shapes as well as thin, open,... Yandong Wen

Haptic Intelligence Talk Andreea Tulbure 10-10-2023 Towards Seamless Handovers with Legged Manipulators Deploying perception and control modules for handovers is challenging because they require a high degree of robustness and generalizability to work reliably for a diversity of objects and situations, but also adaptivity to adjust to individual preferences. On legged robots, deployment is particularly challenging because of the limited computational resources and the additional sensing noise resulting from locomotion. In this talk, I will discuss how we tackle some of these challenges, by first introducing our perception framework and discussing the insights of the first human-robot handover... Katherine J. Kuchenbecker

Haptic Intelligence PhD Thesis Defense 09-10-2023 Gesture-Based Nonverbal Interaction for Exercise Robots When teaching or coaching, humans augment their words with carefully timed hand gestures, head and body movements, and facial expressions to provide feedback to their students. Robots, however, rarely utilize these nuanced cues. A minimally supervised social robot equipped with these abilities could support people in exercising, physical therapy, and learning new activities. This thesis examines how the intuitive power of human gestures can be harnessed to enhance human-robot interaction. To address this question, this research explores gesture-based interactions to expand the capabilities ... Mayumi Mohan Katherine J. Kuchenbecker

Embodied Vision Talk Rama Kandukuri 28-09-2023 Physics-Based Rigid Body Object Tracking and Friction Filtering From RGB-D Videos Physics-based understanding of object interactions from sensory observations is an essential capability in augmented reality and robotics. It enables to capture the properties of a scene for simulation and control. In this paper, we propose a novel approach for real-to-sim which tracks rigid objects in 3D from RGB-D images and infers physical properties of the objects. We use a differentiable physics simulation as state-transition model in an Extended Kalman Filter, which can model contact and friction for arbitrary mesh-based shapes and in this way estimate physically plausible trajectorie... Yandong Wen

Event 14-09-2023 IMPRS-IS 2023 Boot Camp: Mental Health in Academia The 2023 IMPRS-IS Boot Camp will take place from Wednesday, September 13 to Friday, September 15, on the campuses of MPI-IS, the University of Stuttgart, and the University of Tübingen. Mental health awareness in academia is a focus of this year's event with special talk by by clinical psychologist and neuroscientist Dr. Desiree Dickerson, followed by a panel discussion covering the topic. Katherine J. Kuchenbecker Leila Masri Sara Sorce

Event 13-09-2023 IMPRS-IS 2023 Boot Camp: Keynote by Iyad Rahwan The 2023 IMPRS-IS Boot Camp will take place from Wednesday, September 13 to Friday, September 15, on the campuses of MPI-IS, the University of Stuttgart, and the University of Tübingen. A highlight of this year’s boot camp will be a scientific keynote by Dr. Iyad Rahwan, an expert on the future impact of digital technologies. Katherine J. Kuchenbecker Leila Masri Sara Sorce

Perceiving Systems Talk Jun Gao 07-09-2023 Scaling up 3D content generation via 3D grounding for representation, data and algorithm Creating 3D virtual worlds will require generating diverse and high-quality 3D content that mimics the intricacies of the real 3D world. While machine learning has achieved significant success in image and video generation, its application in 3D content generation encounters fundamental challenges in the scarcity of 3D training data and increased complexities inherent in three dimensions. We approach the problem of 3D content generation by revisiting the 3D grounding for the representation, data and algorithms. First, we introduce a differentiable 3D representation that bridges neural field... Yao Feng

Perceiving Systems Talk Yifan Wang 24-08-2023 SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stage A light stage acquires the shape and material properties of a face in high detail using a series of images captured under synchronized cameras and lights. This captured information can be used to synthesize novel images of the subject under arbitrary lighting conditions or from arbitrary viewpoints. This process enables a number of visual effects, such as creating digital replicas of actors that can be used in movies or high-quality postproduction relighting. In many cases, however, it is often infeasible to get access to a light stage for capturing a particular subject, because light stage... Yao Feng

Perceiving Systems Talk Claudia Gallatz 17-08-2023 Face Exploration - Capture all Degrees of Freedom of the Face A high quality data capture is decisive for your scientific work. As a member of the data team, it is a core task of my daily routine to ensure good quality standards in this field. My talk will enlighten the background of this work, starting from scanner set-up and the corresponding data outcome with focus on the Face Scanner. A work, each scientist can profit from for his personal projects. I will take the occasion to present our most recent face capture study named FACE EXPLORATION, of which Timo Bolkart is the leading scientist. A selection of representative sequences including facial m... Yandong Wen

Robotic Materials Talk Prof. Dr. Kyu-Jin Cho 18-07-2023 Nature-inspired designs for innovating soft robotic grippers and prosthetics In this talk, I will discuss the cutting-edge research conducted at our Soft Robotics Research Center and Biorobotics Lab, with an emphasis on the development of grippers and prosthetics inspired by the adaptive behaviors and embodied intelligence observed in nature. Traditional robots are designed for structured environments and navigate unstructured environments using sensors and intricate computation. To adapt to and flourish in unstructured environments, nature employs simple embodied intelligence, which does not necessarily require sensing or complex computation. Christoph Keplinger Metin Sitti

Event 14-07-2023 2023 Intelligent Systems Summer Colloquium & Summer Party The Max Planck Institute for Intelligent Systems is delighted to invite you to its <br> annual scientific summer event & alumni meeting Michael Black Matthias Tröndle Barbara Kettemann Nisha Tyagi

Talk Prof. Dr. Björn Ommer 14-07-2023 Why This is (Not) the End of Research in Generative AI: Stable Diffusion & the Revolution in Visual Synthesis Recently, deep generative modeling has become the most prominent paradigm for learning powerful representations of our (visual) world and for generating novel samples thereof. At the same time, most of the progress came from sizing up models - to the point where the development seemed to be restricted to few big tech companies with boundless resources and with implications on future (academic) research, industry, and society. Michael Black

Workshop 13-07-2023 ELLIS-LAION workshop on foundation models The workshop will take place at the Max Planck Institute for Intelligent Systems on July 13, 2023, supported by ELLIS funding from the state of Baden-Württemberg. It is co-hosted by ELLIS, LAION, and MPI-IS. Bernhard Schölkopf

Perceiving Systems Talk Yangyi Huang 13-07-2023 Full-body avatars from single images and textual guidance The reconstruction of full body appearance of clothed humans from single-view RGB images is a crucial yet challenging task, primarily due to depth ambiguities and the absence of observations from unseen regions. While existing methods have shown impressive results, they still suffer from limitations such as over-smooth surfaces and blurry textures, particularly lacking details at the backside of the avatar. In this talk, I will delve into how we have addressed these limitations by leveraging text guidance and pretrained text-image models, introducing two novel methods. Firstly, I will prese... Hongwei Yi

Haptic Intelligence IS Colloquium Prof. Dangxiao Wang 07-07-2023 Wearable Haptics for Virtual Reality Current virtual reality systems mainly rely on hand-held controllers, which can only provide six-dimensional motion tracking and vibrotactile feedback to users. One promising solution for improving immersion is to develop wearable systems that can capture over 20-DoF hand motion and provide distributed kinesthetic and tactile feedback to the skin. In this talk, I will discuss the technical challenges for developing high-fidelity wearable haptic systems, and then introduce our work on haptic gloves, hand-based haptic rendering algorithms, and the applications of wearable haptic systems in me... Katherine J. Kuchenbecker

Physical Intelligence Talk Dr. Vimal Kishore 04-07-2023 Collective Dynamics: from natural to artificial systems Collective dynamics is referred to as the correlations in the cooperative motion of a many-particle system. It exists on all lengths and time scales and in different systems, ranging from bacteria to robots. Here, the interactions between large numbers of relatively simple individuals result in complex emergent global patterns. The success of these systems is typically associated with their functional robustness and adaptability against perturbations. Here I will discuss swarming with the help of different examples, as viewed from the perspective of the complex system. I will focus on ach... Metin Sitti

Talk Prof. Chris Williams 30-06-2023 Inference and Learning for Generative Capsule Models Capsule networks (see e.g. Hinton et al., 2018) aim to encode knowledge of and reason about the relationship between an object and its parts. Here we specify a generative model for such data, and derive a variational algorithm for inferring the transformation of each model object in a scene, and the assignments of observed parts to the objects. We derive a learning algorithm for the object models, based on variational expectation maximization (Jordan et al., 1999). We also study an alternative inference algorithm based on the RANSAC method of Fischler and Bolles (1981). We apply the...

Social Foundations of Computation Talk Fernando P. Santos 28-06-2023 The impact of link recommendation algorithms on opinion dynamics Celestine Mendler-Dünner

Talk Kirstin Petersen and Nils Napp 12-06-2023 IntCDC Constructive Conversations: "Opportunities in Collective Robotic Construction, viewpoints from the robotics field". The increasing need for safe, inexpensive, and sustainable construction, combined with novel technological enablers, has made large-scale construction by robot teams an active research area. Collective robotic construction (CRC) specifically concerns embodied, autonomous, multirobot systems that modify a shared environment according to high-level user-specified goals. CRC tightly integrates architectural design, the construction process, mechanisms, and control to achieve scalability and adaptability. In this lecture, which is closely tied to the related review article in Science Robotics 2...

Haptic Intelligence Talk Jennifer Leestma 09-06-2023 Biomechanics, Estimation, and Augmentation of Human Balance during Perturbed Locomotion Recent advances in wearable robotics have unveiled the potential of exoskeletons to augment human locomotion across a variety of environments. However, few studies have evaluated the capability of these devices to augment human balance during unstable locomotion. In this talk, I will discuss how we’re threading together biomechanics, mechanical and mechatronic design, wearable sensor-informed machine learning, and controls to work towards a balance-augmenting exoskeleton. I’ll start by discussing human balance, recovery strategies, and some of the most challenging destabilizing scenarios th... Katherine J. Kuchenbecker Andrew Schulz

Max Planck Lecture Yejin Choi 26-05-2023 Common Sense: the Dark Matter of Language and Intelligence The Max Planck Institute for Intelligent Systems is delighted to invite you to its 2023 Max Planck Lecture in Tübingen. Moritz Hardt Michael Black Bernhard Schölkopf Matthias Tröndle Barbara Kettemann Nisha Tyagi

Talk Kirstin Petersen 24-05-2023 Designing Robotic Systems with Collective Embodied Intelligence Natural swarms exhibit sophisticated colony-level behaviors with remarkable scalability and error tolerance. Their evolutionary success stems from more than just intelligent individuals, it hinges on their morphology, their physical interactions, and the way they shape and leverage their environment. Mound-building termites, for instance, are believed to use their own body as a template for construction; the resulting dirt mound serves, among other things, to regulate volatile pheromone cues which in turn guide further construction and colony growth. Throughout this talk I will argue how we... Metin Sitti Barbara Kettemann

Research

Departments

Research Groups

People

Contact

Our Institute

Our History

Career

Doctoral Programs

Training

Service Units

Central Scientific Facilities

Workshops

Campus Services

Impact

Cooperation

Partners and Initiatives