107 citations · 131 across the 44 of their papers we have counts for
15 papers · 1 filter
Where Did the Light Come From? Diagnosing Cast-Shadow Reasoning in VLMs and Borrowing the Missing Shadow Prior from Image Generation Models
Ryugo Morita, Shunsuke Kitada, Stanislav Frolov +5
Shadows are observable consequences of latent physical causes, arising from the interaction between illumination, object geometry, and scene structure. A model that understands sha…
The Self-Improvement Problem
Brian B. Moser, Stanislav Frolov, Tobias C. Nauen +2
With the rise of large language models, agentic systems are becoming increasingly autonomous, as they write code, call tools, revise prompts, and propose modifications to their own…
Walking the Score Manifold: Continuous-time Generative Dynamics on Learned Data Manifolds
Jan Tauberschmidt, Brian B. Moser, Stanislav Frolov +3
Generative modeling of time-dependent data is typically formulated on a discrete temporal grid, restricting supervision to the observed timestamps in the training data. We instead…
Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive
Brian B. Moser, Ahmed Anwar, Tobias Christian Nauen +5
Continual learning regularizers like EWC fight forgetting by penalizing changes from previous-task parameters with per-parameter importance, typically diagonal Fisher values. Per-p…
LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter
Tobias Christian Nauen, Anosh Billimoria, Federico Raue +3
Comparing transformer backbones for image segmentation is confounded: each is paired with a different decoder, recipe, and pretraining, so reported differences rarely reflect the b…
The Gentle Collapse: Distributional Metrics for Continual Learning
Ahmed Anwar, Andreas Wagner, Federico Raue +2
Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not. It saturates at the extremes and collapse…
TaskFusion: Continual Anomaly Detection for Heterogeneous Tabular Data
Dayananda Herurkar, Federico Raue, Joachim Folz +2
Continual anomaly detection in tabular data is challenging and remains largely underexplored, particularly in settings with heterogeneous feature schemas, distribution shifts, and…
OA-CutMix: Correcting the Label Bias of CutMix
Tobias Christian Nauen, Stanislav Frolov, Federico Raue +2
CutMix has become the de facto standard mixing augmentation, yet its label assignment rests on a flawed assumption: The area of the pasted patch faithfully reflects its semantic co…
SegGuidedNet: Sub-Region-Aware Attention Supervision for Interpretable Brain Tumor Segmentation
Hasaan Maqsood, Saif Ur Rehman Khan, Sebastian Vollmer +2
Accurate segmentation of brain tumour sub-regions from multi-parametric MRI is critical for treatment planning yet remains challenging due to morphological variability, class imbal…
TextTeacher: What Can Language Teach About Images?
Tobias Christian Nauen, Stanislav Frolov, Brian Bernhard Moser +3
The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Motivated by this, we ask: Can…
LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency
Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser +4
Layered image assets are widely used in real-world creative workflows, enabling non-destructive iteration and flexible re-composition. Recent advances in layered image generation a…
E-TCAV: Formalizing Penultimate Proxies for Efficient Concept Based Interpretability
Hasib Aslam, Muhammad Ali Chattha, Muhammad Taha Mukhtar +3
TCAV (Testing with Concept Activation Vectors) is an interpretability method that assesses the alignment between the internal representations of a trained neural network and human-…
Hyperspherical Forward-Forward with Prototypical Representations
Shalini Sarode, Brian Moser, Joachim Folz +4
The Forward-Forward (FF) algorithm presents a compelling, bio-inspired alternative to backpropagation. However, while efficient in training, it has a computationally prohibitive in…
LGTM: Training-Free Light-Guided Text-to-Image Diffusion Model via Initial Noise Manipulation
Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser +3
Diffusion models have demonstrated high-quality performance in conditional text-to-image generation, particularly with structural cues such as edges, layouts, and depth. However, l…
When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators
Krzysztof Adamkiewicz, Brian Bernhard Moser, Stanislav Frolov +3
Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as synthetic vision data generator…