Editing complex real-world sound scenes is difficult because individual sound sources overlap in time. Generative models can fill-in missing or corrupted details based on their strong prior understanding of the data domain. We present a system for editing individual sound events within complex scenes able to delete, insert, and enhance individual sound events based on textual edit descriptions (e.g., ``enhance Door'') and a graphical representation of the event timing derived from an ``event roll'' transcription. We present an encoder-decoder transformer working on SoundStream representations, trained on synthetic (input, desired output) audio example pairs formed by adding isolated sound events to dense, real-world backgrounds. Evaluation reveals the importance of each part of the edit descriptions -- action, class, timing. Our work demonstrates ``recomposition'' is an important and practical application.

High-quality textures are critical for realistic 3D content creation, yet existing generative methods are slow, rely on UV maps, and often fail to remain faithful to a reference image. To address these challenges, we propose a transformer-based framework that predicts a 3D texture field directly from a single image and a mesh, eliminating the need for UV mapping and differentiable rendering, and enabling faster texture generation. Our method integrates a triplane representation with depth-based backprojection losses, enabling efficient training and faster inference. Once trained, it generates high-fidelity textures in a single forward pass, requiring only 0.2s per shape. Extensive qualitative, quantitative, and user preference evaluations demonstrate that our method outperforms state-of-the-art baselines on single-image texture reconstruction in terms of both fidelity to the input image and perceptual quality, highlighting its practicality for scalable, high-quality, and controllable 3D content creation.

To advance the development of assistive and rehabilitation robots, it is essential to conduct experiments early in the design cycle. However, testing early prototypes directly with users can pose safety risks. To address this, we explore the use of condition-specific simulation suits worn by healthy participants in controlled environments as a means to study gait changes associated with various impairments and support rapid prototyping. This paper presents a study analyzing the impact of a hemiplegia simulation suit on gait. We collected biomechanical data using a Vicon motion capture system and Delsys Trigno EMG and IMU sensors under four walking conditions: with and without a rollator, and with and without the simulation suit. The gait data was integrated into a digital twin model, enabling machine learning analyses to detect the use of the simulation suit and rollator, identify turning behavior, and evaluate how the suit affects gait over time. Our findings show that the simulation suit significantly alters movement and muscle activation patterns, prompting users to compensate with more abrupt motions. We also identify key features and sensor modalities that are most informative for accurately capturing gait dynamics and modeling human-rollator interaction within the digital twin framework.

Robustifying convolutional neural networks (CNNs) against adversarial attacks remains challenging and often requires resource-intensive countermeasures. W e explore the use of sparse mixture-of-experts (MoE) layers to improve robustness by replacing selected residual blocks or convolu-tional layers, thereby increasing model capacity without additional inference cost. On ResNet architectures trained on CIF AR-100, we find that inserting a single MoE layer in the deeper stages leads to consistent improvements in robustness under PGD and AutoPGD attacks when combined with adversarial training. Furthermore, we discover that when switch loss is used for balancing, it causes routing to collapse onto a small set of overused experts, thereby concentrating adversarial training on these paths and inadvertently making them more robust. As a result, some individual experts outperform the gated MoE model in robustness, suggesting that robust subpaths emerge through specialization. Our code is available at https:// github.com/

The primary paradigm in Neural Combinatorial Optimization (NCO) are construction methods, where a neural network is trained to sequentially add one solution component at a time until a complete solution is constructed. We observe that the typical changes to the state between two steps are small, since usually only the node that gets added to the solution is removed from the state. An efficient model should be able to reuse computation done in prior steps. To that end, we propose to train a recurrent encoder that computes the state embeddings not only based on the state but also the embeddings of the step before. We show that the recurrent encoder can achieve equivalent or better performance than a non-recurrent encoder even if it consists of $3\times$ fewer layers, thus significantly improving on latency. We demonstrate our findings on three different problems: the Traveling Salesman Problem (TSP), the Capacitated Vehicle Routing Problem (CVRP), and the Orienteering Problem (OP) and integrate the models into a large neighborhood search algorithm, to showcase the practical relevance of our findings.

Deictic gestures, like pointing, are a fundamental form of non-verbal communication, enabling humans to direct attention to specific objects or locations. This capability is essential in Human-Robot Interaction (HRI), where robots should be able to predict human intent and anticipate appropriate responses. In this work, we propose the Multi-Modality Inter-TransFormer (MM-ITF), a modular architecture to predict objects in a controlled tabletop scenario with the NICOL robot, where humans indicate targets through natural pointing gestures. Leveraging inter-modality attention, MM-ITF maps 2D pointing gestures to object locations, assigns a likelihood score to each, and identifies the most likely target. Our results demonstrate that the method can accurately predict the intended object using monocular RGB data, thus enabling intuitive and accessible human-robot collaboration. To evaluate the performance, we introduce a patch confusion matrix, providing insights into the model's predictions across candidate object locations. Code available at: https://github.com/lucamuellercode/MMITF.

Developing efficient Vision-Language-Action (VLA) policies is crucial for practical robotics deployment, yet current approaches face prohibitive computational costs and resource requirements. Existing diffusion-based VLA policies require multi-billion-parameter models and massive datasets to achieve strong performance. We tackle this efficiency challenge with two contributions: intermediate-modality fusion, which reallocates capacity to the diffusion head by pruning up to $50\%$ of LLM layers, and action-specific Global-AdaLN conditioning, which cuts parameters by $20\%$ through modular adaptation. We integrate these advances into a novel 950 M-parameter VLA called FLOWER. Pretrained in just 200 H100 GPU hours, FLOWER delivers competitive performance with bigger VLAs across $190$ tasks spanning ten simulation and real-world benchmarks and demonstrates robustness across diverse robotic embodiments. In addition, FLOWER achieves a new SoTA of 4.53 on the CALVIN ABC benchmark. Demos, code and pretrained weights are available at https://intuitive-robots.github.io/flower_vla/.

Deep learning, with its exceptional learning capabilities and flexibility, has been widely applied in various applications. However, its black-box nature poses a significant challenge in real-time robotic applications, particularly in robot control, where trustworthiness and robustness are critical in ensuring safety. In robot motion control, it is essential to analyze and ensure system stability, necessitating the establishment of methodologies that address this need. This paper aims to develop a theoretical framework for end-to-end deep learning control that can be integrated into existing robot control theories. The proposed control algorithm leverages a modular learning approach to update the weights of all layers in real time, ensuring system stability based on Lyapunov-like analysis. Experimental results on industrial robots are presented to illustrate the performance of the proposed deep learning controller. The proposed method offers an effective solution to the black-box problem in deep learning, demonstrating the possibility of deploying real-time deep learning strategies for robot kinematic control in a stable manner. This achievement provides a critical foundation for future advancements in deep learning based real-time robotic applications.

Music adversarial attacks have garnered significant interest in the field of Music Information Retrieval (MIR). In this paper, we present Music Adversarial Inpainting Attack (MAIA), a novel adversarial attack framework that supports both white-box and black-box attack scenarios. MAIA begins with an importance analysis to identify critical audio segments, which are then targeted for modification. Utilizing generative inpainting models, these segments are reconstructed with guidance from the output of the attacked model, ensuring subtle and effective adversarial perturbations. We evaluate MAIA on multiple MIR tasks, demonstrating high attack success rates in both white-box and black-box settings while maintaining minimal perceptual distortion. Additionally, subjective listening tests confirm the high audio fidelity of the adversarial samples. Our findings highlight vulnerabilities in current MIR systems and emphasize the need for more robust and secure models.

Electronic Health Records (EHRs) provide a rich, longitudinal view of patient health and hold significant potential for advancing clinical decision support, risk prediction, and data-driven healthcare research. However, most artificial intelligence (AI) models for EHRs are designed for narrow, single-purpose tasks, limiting their generalizability and utility in real-world settings. Here, we present CEHR-XGPT, a general-purpose foundation model for EHR data that unifies three essential capabilities - feature representation, zero-shot prediction, and synthetic data generation - within a single architecture. To support temporal reasoning over clinical sequences, CEHR-XGPT incorporates a novel time-token-based learning framework that explicitly encodes patients' dynamic timelines into the model structure. CEHR-XGPT demonstrates strong performance across all three tasks and generalizes effectively to external datasets through vocabulary expansion and fine-tuning. Its versatility enables rapid model development, cohort discovery, and patient outcome forecasting without the need for task-specific retraining.