Institute Homepage
Institute Homepage DE Sign In

Publications

DEPARTMENTS

Emperical Interference

Haptic Intelligence

Modern Magnetic Systems

Perceiving Systems

Physical Intelligence

Robotic Materials

Social Foundations of Computation

Research Groups

Autonomous Vision

Autonomous Learning

Bioinspired Autonomous Miniature Robots

Dynamic Locomotion

Embodied Vision

Human Aspects of Machine Learning

Intelligent Control Systems

Learning and Dynamical Systems

Locomotion in Biorobotic and Somatic Systems

Micro, Nano, and Molecular Systems

Movement Generation and Control

Neural Capture and Synthesis

Physics for Inference and Optimization

Organizational Leadership and Diversity

Probabilistic Learning Group

Topics

Robot Learning

Conference Paper

2022

Autonomous Learning

Robotics

AI

Career

Award

Empirical Inference Conference Paper Neural Posterior Estimation of Terrain Parameters from Radar Sounder Data Dal Corso, J., Kofler, A., Cortellazzi, M., Bruzzone, L., Schölkopf, B. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), August 2026 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper Echoes of the Prior: A Computational Phenomenology of Forgetting Gao, G., Schölkopf, B., Geiger, A. Proceedings of the ACM on Computer Graphics and Interactive Techniques: PACM-CGIT, SIGGRAPH, July 2026 (Accepted) Project BibTeX
Haptic Intelligence Organizational Leadership and Diversity Conference Paper Inclusion, Identity, and Impact: Driving Leadership Emergence through Status and Team Dynamics Singh, V., Allemang–Trivalle, A., Cao, C., Nobrega, F. A., Revi, K. N., Kuchenbecker, K. J., Keplinger, K. In Proceedings of the Academy of Management (AOM), 1-9, Philadelphia, USA, July 2026 (Accepted) BibTeX
Empirische Inferenz Conference Paper On the Emergence and Test-Time Use of Structural Information in Large Language Models Chen, M. C., Miller, M., Schölkopf, B., Guo, S. 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), July 2026 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper Differentiable Simulation of Hard Contacts with Soft Gradients for Learning and Control Paulus*, A., Geist*, A. R., Schumacher*, P., Rappenecker, S., Musil, V., Martius, G. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *equal contribution (Published) arXiv URL BibTeX
Empirical Inference Conference Paper Estimating Joint Interventional Distributions from Marginal Interventional Data Garrido Mejia, S., Kirschbaum, E., Kekić, A., Schölkopf, B., Mastakouri, A. A. Proceedings of the Fifth Conference on Causal Learning and Reasoning, 323:1-23, PMLR, 5th Conference on Causal Learning and Reasoning, April 2026 (To be published) arXiv BibTeX
Empirical Inference Conference Paper Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies Kekić, A., Schneider, J., Büchler, D., Schölkopf*, B., Besserve*, M. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *joint supervision (Published) arXiv URL BibTeX
Empirical Inference Conference Paper Proper Velocity Neural Networks Chen*, Z., Su*, Z., Schölkopf, B., Sebe, N. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *equal contribution (Published) URL BibTeX
Social Foundations of Computation Conference Paper ROC-n-reroll: How Verifier Imperfection affects Test-Time Scaling Dorner, F. E., Chen, Y. C., Cruz, A. F., Yang, F. Y. The Fourteenth International Conference on Learning Representations (ICLR), April 2026 (Accepted)
Test-time scaling aims to improve language model performance by leveraging additional compute during inference. Many works have empirically studied techniques such as Best-of-N (BoN) and Rejection Sampling (RS) that make use of a verifier to enable test-time scaling. However, to date there is little theoretical understanding of how verifier imperfection affects performance -- a gap we address in this work. Specifically, we prove that the instance-level accuracy of these methods is precisely characterized by the geometry of the verifier's ROC curve. Our theory has two important takeaways, confirmed by experiments with Qwen and LLama models on GSM8K and MATH500. First, RS outperforms BoN for fixed compute, while both methods converge to the same accuracy in the infinite-compute limit. Second, it is generally impossible to predict the high-compute performance of either method based on observations in the low-compute regime.
arXiv BibTeX
Empirical Inference Conference Paper Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles Ni*, Z., Li*, Y., Qiu*, Z., Schölkopf, B., Guo, H., Liu, W., Liu, S. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *equal contribution (Published) arXiv URL BibTeX
Empirical Inference Deep Models and Optimization Conference Paper Scaling Behavior of Discrete Diffusion Language Models von Rütte, D., Fluri, J., Pooladzandi, O., Schölkopf, B., Hofmann, T., Orvieto, A. The Fourteenth International Conference on Learning Representations (ICLR), April 2026 (Published) arXiv URL BibTeX
Empirical Inference Robust Machine Learning Conference Paper Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning Reizinger*, P., Mucsányi*, B., Guo*, S., Eysenbach, B., Schölkopf, B., Brendel, W. The Fourteenth International Conference on Learning Representations (ICLR), April 2026, *equal contribution (Published) arXiv URL BibTeX
Empirical Inference Conference Paper SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests Pandey, P. S., Le, H. S., Bhardwaj, D., Mihalcea, R., Zhijing, J. The Fourteenth International Conference on Learning Representations (ICLR), April 2026 (Published) arXiv URL BibTeX
Perceiving Systems Conference Paper Predicting 4D Hand Trajectory from Monocular Videos Ye, Y., Feng, Y., Taheri, O., Feng, H., Black, M. J., Tulsiani, S. In Int. Conf. on 3D Vision (3DV), March 2026 (Accepted)
We present HAPTIC, an approach that infers coherent 4D hand trajectories from monocular videos. Current video-based hand pose reconstruction methods primarily focus on improving frame-wise 3D pose using adjacent frames rather than studying consistent 4D hand trajectories in space. Despite the additional temporal cues, they generally underperform compared to image-based methods due to the scarcity of annotated video data. To address these issues, we repurpose a state-of-the-art image-based transformer to take in multiple frames and directly predict a coherent trajectory. We introduce two types of lightweight attention layers: cross-view self-attention to fuse temporal information, and global cross-attention to bring in larger spatial context. Our method infers 4D hand trajectories similar to the ground truth while maintaining strong 2D reprojection alignment. We apply the method to both egocentric and allocentric videos. It significantly outperforms existing methods in global trajectory accuracy while being comparable to the state-of-the-art in single-image pose estimation.
project arXiv code BibTeX
Perceiving Systems Conference Paper Supervising 3D Talking Head Avatars with Analysis-by-Audio-Synthesis Danecek, R., Schmitt, C., Polikovsky, S., Black, M. J. In Int. Conf. on 3D Vision (3DV), March 2026 (Accepted)
In order to be widely applicable, speech-driven 3D head avatars must articulate their lips in accordance with speech, while also conveying the appropriate emotions with dynamically changing facial expressions. The key problem is that deterministic models produce high-quality lip-sync but without rich expressions, whereas stochastic models generate diverse expressions but with lower lip-sync quality. To get the best of both, we seek a stochastic model with accurate lip-sync. To that end, we develop a new approach based on the following observation: if a method generates realistic 3D lip motions, it should be possible to infer the spoken audio from the lip motion. The inferred speech should match the original input audio, and erroneous predictions create a novel supervision signal for training 3D talking head avatars with accurate lip-sync. To demonstrate this effect, we propose THUNDER (Talking Heads Under Neural Differentiable Elocution Reconstruction), a 3D talking head avatar framework that introduces a novel supervision mechanism via differentiable sound production. First, we train a novel mesh-to-speech model that regresses audio from facial animation. Then, we incorporate this model into a diffusion-based talking avatar framework. During training, the mesh-to-speech model takes the generated animation and produces a sound that is compared to the input speech, creating a differentiable analysis-by-audio-synthesis supervision loop. Our extensive qualitative and quantitative experiments demonstrate that THUNDER significantly improves the quality of the lip-sync of talking head avatars while still allowing for generation of diverse, high-quality, expressive facial animations.
project arXiv BibTeX
Perceiving Systems Conference Paper NeuralFur: Animal Fur Reconstruction from Multi-view Images Sklyarova, V., Kabadayi, B., Yiannakidis, A., Becherini, G., Black, M. J., Thies, J. In Int. Conf. on 3D Vision (3DV), March 2026 (Accepted)
Reconstructing realistic animal fur geometry from images is a challenging task due to the fine-scale details, self-occlusion, and view-dependent appearance of fur. In contrast to human hairstyle reconstruction, there are also no datasets that could be leveraged to learn a fur prior for different animals. In this work, we present a first multi-view-based method for high-fidelity 3D fur modeling of animals using a strand-based representation, leveraging the general knowledge of a vision language model. Given calibrated multi-view RGB images, we first reconstruct a coarse surface geometry using traditional multi-view stereo techniques. We then use a visual question answering (VQA) system to retrieve information about the realistic length structure of the fur for each part of the body. We use this knowledge to construct the animal’s furless geometry and grow strands atop it. The fur reconstruction is supervised with both geometric and photometric losses computed from multi-view images. To mitigate orientation ambiguities stemming from the Gabor filters that are applied to the input images, we additionally utilize the VQA to guide the strands' growth direction and their relation to the gravity vector that we incorporate as a loss. With this new schema of using a VQA model to guide 3D reconstruction from multi-view inputs, we show generalization across a variety of animals with different fur types.
project arXiv code BibTeX
Haptic Intelligence Conference Paper Designing a Psychotherapy Support Robot for Young Children Diagnosed with Obsessive-Compulsive Disorder Mohan, M., L’Orsa, R., Grüninger, F., Stollhof, B., Klein, C. S., Dinauer, R., Burns, R. B., Renner, T. J., Hollmann, K., Kuchenbecker, K. J. In Companion Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction (HRI), 1-6, Late-Breaking Report (LBR) (6 pages) presented at the IEEE/ACM International Conference on Human-Robot Interaction (HRI), Edinburgh, UK, March 2026, Mayumi Mohan and Rachael L'Orsa contributed equally to this publication (Published)
The gold-standard treatment for children diagnosed with obsessive-compulsive disorder (OCD) is therapist-guided cognitive behavioral therapy (CBT), which includes exposure and response prevention (ERP) sessions that teach children to overcome compulsive responses when exposed to their anxiety-inducing triggers. CBT requires children to report frequent self-assessments of tension during both therapist-supported and therapist-free self-management ERP sessions. Videoconferencing-delivered CBT (vCBT) enables a psychotherapist to treat a child remotely in their home, where OCD symptoms often arise, but these remote therapeutic interactions lack physical presence and can be challenging to run. We propose using a robot as an input/output device during vCBT for young children diagnosed with OCD, and we introduce a stationary table-top koala robot for this application. We further describe the first of three planned participatory design phases: a co-design study comprising two sessions where child and adolescent psychotherapists role-played vCBT ERP exercises with this robot to help define its role.
DOI BibTeX
Empirical Inference Conference Paper Sim-to-Real for Muscle-Actuated Robots via Learned Actuator Models Schneider, J., Mahajan, M., Chen, L., Guist, S., Schölkopf, B., Posner, I., Büchler, D. 2nd German Robotics Conference (GRC), March 2026 (Published) URL BibTeX
Social Foundations of Computation Conference Paper Train-before-Test Harmonizes Language Model Rankings Zhang, G., Dominguez-Olmedo, R., Hardt, M. The Fourteenth International Conference on Learning Representations (ICLR), oral, Top1.18%, January 2026 (Accepted)
Existing language model benchmarks provide contradictory model rankings, even for benchmarks that aim to capture similar skills. This dilemma of conflicting rankings hampers model selection, clouds model comparisons, and adds confusion to a growing ecosystem of competing models. Recent work attributed ranking disagreement to the phenomenon of training on the test task: As released, different models exhibit a different level of preparation for any given test task. A candidate solution to the problem is train-before-test: Give each model the same benchmark-specific finetuning before evaluation. Our primary contribution is a broad empirical evaluation of train-before-test across 24 benchmarks and 61 models. We show that train-before-test significantly improves ranking agreement consistently across all benchmarks. Whereas rankings have little external validity to start with, they enjoy a significant degree of external validity when applying train-before-test: Model rankings transfer gracefully from one benchmark to the other. Even within the same model family, train-before-test reduces strong ranking disagreement to near-perfect agreement. In addition, train-before-test reduces the model-score matrix to essentially rank one, revealing new insights into the latent factors of benchmark performance. Our work supports the recommendation to make train-before-test a default component of LLM benchmarking.
arXiv BibTeX
Perceiving Systems Conference Paper BEDLAM2.0: Synthetic humans and cameras in motion Tesch, J., Becherini, G., Achar, P., Yiannakidis, A., Kocabas, M., Patel, P., Black, M. J. In Advances in Neural Information Processing Systems (NeurIPS), Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track, December 2025 (Published)
Inferring 3D human motion from video remains a challenging problem with many applications. While traditional methods estimate the human in image coordinates, many applications require human motion to be estimated in world coordinates. This is particularly challenging when there is both human and camera motion. Progress on this topic has been limited by the lack of rich video data with ground truth human and camera movement. We address this with BEDLAM2.0, a new dataset that goes beyond the popular BEDLAM dataset in important ways. In addition to introducing more diverse and realistic cameras and camera motions, BEDLAM2.0 increases diversity and realism of body shape, motions, clothing, hair, and 3D environments. Additionally, it adds shoes, which were missing in BEDLAM. BEDLAM has become a key resource for training 3D human pose and motion regressors today and we show that BEDLAM2.0 is significantly better, particularly for training methods that estimate humans in world coordinates. We compare state-of-the art methods trained on BEDLAM and BEDLAM2.0, and find that BEDLAM2.0 significantly improves accuracy over BEDLAM. For research purposes, we provide the rendered videos, ground truth body parameters, and camera motions. We also provide the 3D assets to which we have rights and links to those from third parties.
Project Paper Video URL BibTeX
Perceiving Systems Conference Paper HairFree: Compositional 2D Head Prior for Text-Driven 360° Bald Texture Synthesis Ostrek, M., Black, M., Thies, J. In Advances in Neural Information Processing Systems (NeurIPS), Advances in Neural Information Processing Systems (NeurIPS), December 2025 (Published)
Synthesizing high-quality 3D head textures is crucial for gaming, virtual reality, and digital humans. Achieving seamless 360° textures typically requires expensive multi-view datasets with precise tracking. However, traditional methods struggle without back-view data or precise geometry, especially for human heads, where even minor inconsistencies disrupt realism. We introduce HairFree, an unsupervised texturing framework guided by textual descriptions and 2D diffusion priors, producing high-consistency 360° bald head textures—including non-human skin with fine details—without any texture, back-view, bald, non-human, or synthetic training data. We fine-tune a diffusion prior on a dataset of mostly frontal faces, conditioned on predicted 3D head geometry and face parsing. During inference, HairFree uses precise skin masks and 3D FLAME geometry as input conditioning, ensuring high 3D consistency and alignment. We synthesize the full 360° texture by first generating a frontal RGB image aligned to the 3D FLAME pose and mapping it to UV space. As the virtual camera moves, we inpaint and merge missing regions. A built-in semantic prior enables precise region separation—particularly for isolating and removing hair—allowing seamless integration with various assets like customizable 3D hair, eyeglasses, jewelry, etc. We evaluate HairFree quantitatively and qualitatively, demonstrating its superiority over state-of-the-art 3D head avatar generation methods. https://hairfree.is.tue.mpg.de/
pdf project poster BibTeX
Perceiving Systems Conference Paper GenLit: Reformulating Single Image Relighting as Video Generation Bharadwaj, S., Feng, H., Becherini, G., Abrevaya, V. F., Black, M. J. In SIGGRAPH Asia Conference Papers ’25, Association for Computing Machinery, SIGGRAPH Asia, December 2025 (To be published)
Manipulating the illumination of a 3D scene within a single image represents a fundamental challenge in computer vision and graphics. This problem has traditionally been addressed using inverse rendering techniques, which involve explicit 3D asset reconstruction and costly ray-tracing simulations. Meanwhile, recent advancements in visual foundation models suggest that a new paradigm could soon be possible -- one that replaces explicit physical models with networks that are trained on large amounts of image and video data. In this paper, we exploit the implicit scene understanding of a video diffusion model, particularly Stable Video Diffusion, to relight a single image. We introduce GenLit, a framework that distills the ability of a graphics engine to perform light manipulation into a video-generation model, enabling users to directly insert and manipulate a point light in the 3D world within a given image and generate results directly as a video sequence. We find that a model fine-tuned on only a small synthetic dataset generalizes to real-world scenes, enabling single-image relighting with plausible and convincing shadows and inter-reflections. Our results highlight the ability of video foundation models to capture rich information about lighting, material, and shape, and our findings indicate that such models, with minimal training, can be used to perform relighting without explicit asset reconstruction or ray-tracing.
Project Page Paper DOI URL BibTeX
Empirical Inference Conference Paper A data and task-constrained mechanistic model of the mouse outer retina shows robustness to contrast variations Kadhim, K. L., Beck, J., Huang, Z., Macke, J. H., Rieke, F., Euler, T., Deistler, M., Berens, P. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) bioRxiv BibTeX
Empirical Inference Conference Paper Are Language Models Efficient Reasoners? A Perspective from Logic Programming Opedal, A., Zengaffinen, Y., Shirakami, H., Pasti, C., Sachan, M., Saparov, A., Cotterell, R., Schölkopf, B. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper CauSciBench: Assessing LLM Causal Reasoning for Scientific Research Acharya, S., Zhang, T. J., Kim, A., Haghighat, A., Sun, X., Shrestha, R. B., Mordig, M., Danisman, F., Jose, C., Qi, Y., Cobben, P., Schölkopf, B., Sachan, M., Jin, Z. NeurIPS 2025: 5th Workshop on Mathematical Reasoning and AI (Math-AI) and CauScien Workshop, December 2025 (Published) URL BibTeX
Empirical Inference Conference Paper Counterfactual reasoning: an analysis of in-context emergence Miller, M., Schölkopf, B., Guo, S. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper Cultural Alien Sampler: Open-ended art generation balancing originality and coherence Hernandez, A., Yakura, H., Brinkmann, L., Sola, M. C., Alhaija, H. A., Serna, I., Rahaman, N., Schölkopf, B., Rahwan, I. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, Creative AI Track, December 2025 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper Do-PFN: In-Context Learning for Causal Effect Estimation Robertson*, J., Reuter*, A., Guo, S., Hollmann, N., Hutter, F., Schölkopf, B. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025, *equal contribution (Accepted) arXiv BibTeX
Empirical Inference Conference Paper Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models Vetter, J., Gloeckler, M., Gedon, D., Macke, J. H. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper FNOPE: Simulation-based inference on function spaces with Fourier Neural Operators Moss, G., Muhle, L. S., Drews, R., Macke, J. H., Schröder, C. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper Forecasting in Offline Reinforcement Learning for Non-stationary Environments Ada, S. E., Martius, G., Ugur, E., Oztop, E. In Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper Identifying multi-compartment Hodgkin-Huxley models with high-density extracellular voltage recordings Tanoh, I. C., Deistler, M., Macke, J. H., Linderman, S. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper Reparameterized LLM Training via Orthogonal Equivalence Transformation Qiu, Z., Buchholz, S., Xiao, T., Dax, M., Schölkopf, B., Liu, W. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper Root Cause Analysis of Outliers with Missing Structural Knowledge Orchard, W. R., Okati, N., Garrido Mejia, S., Blöbaum, P., Janzing, D. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX
Empirical Inference Conference Paper SPARTAN: A Sparse Transformer World Model Attending to What Matters Lei, A., Schölkopf, B., Posner, I. Advances in Neural Information Processing Systems 38 (NeurIPS 2025), 39th Annual Conference on Neural Information Processing Systems, December 2025 (Accepted) arXiv BibTeX
Organizational Leadership and Diversity Conference Paper Inclusive Leadership in the Age of AI: A Dataset and Comparative Study of LLMs vs. Real-Life Leaders in Workplace Action Planning Singh, V., Schulte im Walde, S., Keplinger, K. Findings of the Association for Computational Linguistics: EMNLP 2025, 19732-19753, Association for Computational Linguistics, Suzhou, China, Empirical Methods in Natural Language Processing, November 2025 (Published)
Generative Large Language Models have emerged as useful tools, reshaping professional workflows. However, their efficacy in inherently complex and human-centric tasks such as leadership and strategic planning remains under-explored. In this interdisciplinary study, we present a novel dataset and compare LLMs and human leaders in the context of work-place action planning, specifically focusing on translating the abstract idea of inclusion into actionable SMART goals. We developed the Leader Success Bot, a script-based chat-bot co-designed with domain experts, to guide more than 250 real-life leaders in generating inclusive workplace action plans. We systematically prompted seven state-of-the-art chat-based LLMs to perform the same task using the socio-demographic data of real-life leaders and instructions co-developed with domain experts. Our publicly released dataset enables direct comparison between human and LLM-generated workplace action plans, offering in-sights into their respective strengths, biases, and limitations. Our findings highlight critical gaps and opportunities for LLMs in leadership applications, fostering interdisciplinary collaboration and NLP applications.
DOI URL BibTeX
Empirical Inference Conference Paper Improving Large Language Model Safety with Contrastive Representation Learning Simko, S., Sachan, M., Schölkopf, B., Jin, Z. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 28166-28194, (Editors: Christodoulopoulos, Christos and Chakraborty, Tanmoy and Rose, Carolyn and Peng, Violet), Association for Computational Linguistics, November 2025 (Published) arXiv DOI URL BibTeX
Haptic Intelligence Perceiving Systems Conference Paper Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing Forte, M., Athanasiou, N., Ballardini, G., Bartels, J. U., Kuchenbecker, K. J., Black, M. J. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 5071-5080, Honolulu, USA, October 2025, Nikos Athanasiou and Giulia Ballardini contributed equally to this publication (Published) pdf URL BibTeX
Haptic Intelligence Intelligent Control Systems Conference Paper Diffusion-Based Approximate MPC: Fast and Consistent Imitation of Multi-Modal Action Distributions Marquez Julbe, P., Nubert, J., Hose, H., Trimpe, S., Kuchenbecker, K. J. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 5633-5640, Hangzhou, China, October 2025 (Published)
Approximating model predictive control (MPC) using imitation learning (IL) allows for fast control without solving expensive optimization problems online. However, methods that use neural networks in a simple L2-regression setup fail to approximate multi-modal (set-valued) solution distributions caused by local optima found by the numerical solver or non-convex constraints, such as obstacles, significantly limiting the applicability of approximate MPC in practice. We solve this issue by using diffusion models to accurately represent the complete solution distribution (i.e., all modes) at high control rates (more than 1000 Hz). This work shows that diffusion-based AMPC significantly outperforms L2-regression-based approximate MPC for multi-modal action distributions. In contrast to most earlier work on IL, we also focus on running the diffusion-based controller at a higher rate and in joint space instead of end-effector space. Additionally, we propose the use of gradient guidance during the denoising process to consistently pick the same mode in closed loop to prevent switching between solutions. We propose using the cost and constraint satisfaction of the original MPC problem during parallel sampling of solutions from the diffusion model to pick a better mode online. We evaluate our method on the fast and accurate control of a 7-DoF robot manipulator both in simulation and on hardware deployed at 250 Hz, achieving a speedup of more than 70 times compared to solving the MPC problem online and also outperforming the numerical optimization (used for training) in success ratio.
DOI BibTeX
Perceiving Systems Conference Paper Generative Zoo Niewiadomski, T., Yiannakidis, A., Cuevas-Velasquez, H., Sanyal, S., Black, M. J., Zuffi, S., Kulits, P. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Honolulu, HI, International Conference on Computer Vision, ICCV, October 2025 (Published)
The model-based estimation of 3D animal pose and shape from images enables computational modeling of animal behavior. Training models for this purpose requires large amounts of labeled image data with precise pose and shape annotations. However, capturing such data requires the use of multi-view or marker-based motion-capture systems, which are impractical to adapt to wild animals in situ and impossible to scale across a comprehensive set of animal species. Some have attempted to address the challenge of procuring training data by pseudo-labeling individual real-world images through manual 2D annotation, followed by 3D-parameter optimization to those labels. While this approach may produce silhouette-aligned samples, the obtained pose and shape parameters are often implausible due to the ill-posed nature of the monocular fitting problem. Sidestepping real-world ambiguity, others have designed complex synthetic-data-generation pipelines leveraging video-game engines and collections of artist-designed 3D assets. Such engines yield perfect ground-truth annotations but are often lacking in visual realism and require considerable manual effort to adapt to new species or environments. Motivated by these shortcomings, we propose an alternative approach to synthetic-data generation: rendering with a conditional image-generation model. We introduce a pipeline that samples a diverse set of poses and shapes for a variety of mammalian quadrupeds and generates realistic images with corresponding ground-truth pose and shape parameters. To demonstrate the scalability of our approach, we introduce GenZoo, a synthetic dataset containing one million images of distinct subjects. We train a 3D pose and shape regressor on GenZoo, which achieves state-of-the-art performance on a real-world multi-species 3D animal pose and shape estimation benchmark, despite being trained solely on synthetic data. We will release our dataset and generation pipeline to support future research.
project page code demo pdf BibTeX
Perceiving Systems Conference Paper ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness Li, B., Feng, H., Cai, Z., Black, M. J., Xiu, Y. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2025 (Published)
itting a body to a 3D clothed human point cloud is a common yet challenging task. Traditional optimization-based approaches use multi-stage pipelines that are sensitive to pose initialization, while recent learning-based methods often struggle with generalization across diverse poses and garment types. We propose Equivariant Tightness Fitting for Clothed Humans, or ETCH, a novel pipeline that estimates cloth-to-body surface mapping through locally approximate SE(3) equivariance, encoding tightness as displacement vectors from the cloth surface to the underlying body. Following this mapping, pose-invariant body features regress sparse body markers, simplifying clothed human fitting into an inner-body marker fitting task. Extensive experiments on CAPE and 4D-Dress show that ETCH significantly outperforms state-of-the-art methods -- both tightness-agnostic and tightness-aware -- in body fitting accuracy on loose clothing (16.7% ~ 69.5%) and shape accuracy (average 49.9%). Our equivariant tightness design can even reduce directional errors by (67.2% ~ 89.8%) in one-shot (or out-of-distribution) settings (~ 1% data). Qualitative results demonstrate strong generalization of ETCH, regardless of challenging poses, unseen shapes, loose clothing, and non-rigid dynamics.
project arXiv code video BibTeX
Perceiving Systems Conference Paper Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars Vanessa, S., Egor, Z., Malte, P., Giorgio, B., Michael, B., Justus, T. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Honolulu, USA, October 2025 (Accepted)
We present a novel approach for 3D hair reconstruction from single photographs based on a global hair prior combined with local optimization. Capturing strand-based hair geometry from single photographs is challenging due to the variety and geometric complexity of hairstyles and the lack of ground truth training data. Classical reconstruction methods like multi-view stereo only reconstruct the visible hair strands, missing the inner structure of hairstyles and hampering realistic hair simulation. To address this, existing methods leverage hairstyle priors trained on synthetic data. Such data, however, is limited in both quantity and quality since it requires manual work from skilled artists to model the 3D hairstyles and create near-photorealistic renderings. To address this, we propose a novel approach that uses both, real and synthetic data to learn an effective hairstyle prior. Specifically, we train a transformer-based prior model on synthetic data to obtain knowledge of the internal hairstyle geometry and introduce real data in the learning process to model the outer structure. This training scheme is able to model the visible hair strands depicted in an input image, while preserving the general 3D structure of hairstyles. We exploit this prior to create a Gaussian-splatting-based reconstruction method that creates hairstyles from one or more images. Qualitative and quantitative comparisons with existing reconstruction pipelines demonstrate the effectiveness and superior performance of our method for capturing detailed hair orientation, overall silhouette, and backside consistency. For additional results and code, please refer to https://im2haircut.is.tue.mpg.de.
arXiv project code BibTeX
Perceiving Systems Conference Paper MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips Wang, S., He, H., Parelli, M., Gebhardt, C., Fan, Z., Song, J. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), ICCV, October 2025 (Published)
Most RGB-based hand-object reconstruction methods rely on object templates, while template-free methods typically assume full object visibility. This assumption often breaks in real-world settings, where fixed camera viewpoints and static grips leave parts of the object unobserved, resulting in implausible reconstructions. To overcome this, we present MagicHOI, a method for reconstructing hands and objects from short monocular interaction videos, even under limited viewpoint variation. Our key insight is that, despite the scarcity of paired 3D hand-object data, largescale novel view synthesis diffusion models offer rich object supervision. This supervision serves as a prior to regularize unseen object regions during hand interactions. Leveraging this insight, we integrate a novel view synthesis model into our hand-object reconstruction framework. We further align hand to object by incorporating visible contact constraints. Our results demonstrate that MagicHOI significantly outperforms existing state-of-the-art hand-object reconstruction methods. We also show that novel view synthesis diffusion priors effectively regularize unseen object regions, enhancing 3D hand-object reconstruction.
Project Video Code URL BibTeX
Perceiving Systems Conference Paper MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction Dong, Z., Duan, L., Song, J., Black, M. J., Geiger, A. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2025 (Published)
We present MoGA, a novel method to reconstruct high-fidelity 3D Gaussian avatars from a single-view image. The main challenge lies in inferring unseen appearance and geometric details while ensuring 3D consistency and realism. Most previous methods rely on 2D diffusion models to synthesize unseen views; however, these generated views are sparse and inconsistent, resulting in unrealistic 3D artifacts and blurred appearance. To address these limitations, we leverage a generative avatar model, that can generate diverse 3D avatars by sampling deformed Gaussians from a learned prior distribution. Due to the limited amount of 3D training data such a 3D model alone cannot capture all image details of unseen identities. Consequently, we integrate it as a prior, ensuring 3D consistency by projecting input images into its latent space and enforcing additional 3D appearance and geometric constraints. Our novel approach formulates Gaussian avatar creation as a model inversion process by fitting the generative avatar to synthetic views from 2D diffusion models. The generative avatar provides a meaningful initialization for model fitting, enforces 3D regularization, and helps in refining pose estimation. Experiments show that our method surpasses state-of-the-art techniques and generalizes well to real-world scenarios. Our Gaussian avatars are also inherently animatable.
pdf project code video BibTeX
Perceiving Systems Conference Paper PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning Zhang, Y., Feng, Y., Cseke, A., Saini, N., Bajandas, N., Heron, N., Black, M. J. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2025 (Published)
We formulate the motor system of an interactive avatar as a generative motion model that can drive the body to move through 3D space in a perpetual, realistic, controllable, and responsive manner. Although human motion generation has been extensively studied, many existing methods lack the responsiveness and realism of real human movements. Inspired by recent advances in foundation models, we propose PRIMAL, which is learned with a two-stage paradigm. In the pretraining stage, the model learns body movements from a large number of sub-second motion segments, providing a generative foundation from which more complex motions are built. This training is fully unsupervised without annotations. Given a single-frame initial state during inference, the pretrained model not only generates unbounded, realistic, and controllable motion, but also enables the avatar to be responsive to induced impulses in real time. In the adaptation phase, we employ a novel ControlNet-like adaptor to fine-tune the base model efficiently, adapting it to new tasks such as few-shot personalized action generation and spatial target reaching. Evaluations show that our proposed method outperforms state-of-the-art baselines. We leverage the model to create a real-time character animation system in Unreal Engine that feels highly responsive and natural.
pdf project code video BibTeX
Perceiving Systems Conference Paper SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image Antić, D., Paschalidis, G., Tripathi, S., Gevers, T., Dwivedi, S. K., Tzionas, D. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2025 (Published)
Recovering 3D object pose and shape from a single image is a challenging and ill-posed problem. This is due to strong (self-)occlusions, depth ambiguities, the vast intra- and inter-class shape variance, and the lack of 3D ground truth for natural images. Existing deep-network methods are trained on synthetic datasets to predict 3D shapes, so they often struggle generalizing to real-world images. Moreover, they lack an explicit feedback loop for refining noisy estimates, and primarily focus on geometry without directly considering pixel alignment. To tackle these limitations, we develop a novel render-and-compare optimization framework, called SDFit. This has three key innovations: First, it uses a learned category-specific and morphable signed-distance-function (mSDF) model, and fits this to an image by iteratively refining both 3D pose and shape. The mSDF robustifies inference by constraining the search on the manifold of valid shapes, while allowing for arbitrary shape topologies. Second, SDFit retrieves an initial 3D shape that likely matches the image, by exploiting foundational models for efficient look-up into 3D shape databases. Third, SDFit initializes pose by establishing rich 2D-3D correspondences between the image and the mSDF through foundational features. We evaluate SDFit on three image datasets, i.e., Pix3D, Pascal3D+, and COMIC. SDFit performs on par with SotA feed-forward networks for unoccluded images and common poses, but is uniquely robust to occlusions and uncommon poses. Moreover, it requires no retraining for unseen images. Thus, SDFit contributes new insights for generalizing in the wild.
Project arXiv Code Video Poster BibTeX
Perceiving Systems Conference Paper St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World Feng, H., Zhang, J., Wang, Q., Ye, Y., Yu, P., Black, M., Darrell, T., Kanazawa, A. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2025 (Published)
Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection. We propose St4RTrack, a feed-forward framework that simultaneously reconstructs and tracks dynamic video content in a world coordinate frame from RGB inputs. This is achieved by predicting two appropriately defined pointmaps for a pair of frames captured at different moments. Specifically, we predict both pointmaps at the same moment, in the same world, capturing both static and dynamic scene geometry while maintaining 3D correspondences. Chaining these predictions through the video sequence with respect to a reference frame naturally computes long-range correspondences, effectively combining 3D reconstruction with 3D tracking. Unlike prior methods that rely heavily on 4D ground truth supervision we employ a novel adaptation scheme based on a reprojection loss. We establish a new extensive benchmark for world-frame reconstruction and tracking, demonstrating the effectiveness and efficiency of our unified, data-driven framework.
pdf arXiv project code demo video BibTeX
Haptic Intelligence Autonomous Learning Empirical Inference Conference Paper Adding Internal Audio Sensing to Internal Vision Enables Human-Like In-Hand Fabric Recognition with Soft Robotic Fingertips Andrussow, I., Solano, J., Richardson, B. A., Martius, G., Kuchenbecker, K. J. In Proceedings of the IEEE-RAS International Conference on Humanoid Robots (Humanoids), 373-380, Seoul, South Korea, September 2025 (Published)
Distinguishing the feel of smooth silk from coarse cotton is a trivial everyday task for humans. When exploring such fabrics, fingertip skin senses both spatio-temporal force patterns and texture-induced vibrations that are integrated to form a haptic representation of the explored material. It is challenging to reproduce this rich, dynamic perceptual capability in robots because tactile sensors typically cannot achieve both high spatial resolution and high temporal sampling rate. In this work, we present a system that can sense both types of haptic information, and we investigate how each type influences robotic tactile perception of fabrics. Our robotic hand's middle finger and thumb each feature a soft tactile sensor: one is the open- source Minsight sensor that uses an internal camera to measure fingertip deformation and force at 50 Hz, and the other is our new sensor Minsound that captures vibrations through an internal MEMS microphone with a bandwidth from 50 Hz to 15 kHz. Inspired by the movements humans make to evaluate fabrics, our robot actively encloses and rubs folded fabric samples between its two sensitive fingers. Our results test the influence of each sensing modality on overall classification performance, showing high utility for the audio-based sensor. Our transformer-based method achieves a maximum fabric classification accuracy of 97% on a dataset of 20 common fabrics. Incorporating an external microphone away from Minsound increases our method's robustness in loud ambient noise conditions. To show that this audio-visual tactile sensing approach generalizes beyond the training data, we learn general representations of fabric stretchiness, thickness, and roughness.
DOI BibTeX
Haptic Intelligence Robotics Embodied Vision Conference Paper ISyHand: A Dexterous Multi-finger Robot Hand with an Articulated Palm Richardson, B. A., Grüninger, F., Mack, L., Stueckler, J., Kuchenbecker, K. J. In Proceedings of the IEEE-RAS International Conference on Humanoid Robots (Humanoids), 720-727, Seoul, South Korea, September 2025, Benjamin A. Richardson, Felix Grueninger and Lukas Mack contributed equally to this publication (Published) DOI BibTeX
Social Foundations of Computation Conference Paper Strategic Hypothesis Testing Hossain, S., Chen, Y., Chen, Y. The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS), Spotlight Poster, top 3%, September 2025 (Accepted)
We examine hypothesis testing within a principal-agent framework, where a strategic agent, holding private beliefs about the effectiveness of a product, submits data to a principal who decides on approval. The principal employs a hypothesis testing rule, aiming to pick a p-value threshold that balances false positives and false negatives while anticipating the agent's incentive to maximize expected profitability. Building on prior work, we develop a game-theoretic model that captures how the agent's participation and reporting behavior respond to the principal's statistical decision rule. Despite the complexity of the interaction, we show that the principal's errors exhibit clear monotonic behavior when segmented by an efficiently computable critical p-value threshold, leading to an interpretable characterization of their optimal p-value threshold. We empirically validate our model and these insights using publicly available data on drug approvals. Overall, our work offers a comprehensive perspective on strategic interactions within the hypothesis testing framework, providing technical and regulatory insights.
arXiv BibTeX