5 papers
Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI
Quang Bui, Shlok Jaiswal, Samuel Paik-Heintz +14
Multimodal clinical models are usually judged on accuracy with every modality present, but deployment removes modalities; an echocardiogram is often unavailable where an ECG is rou…
Structure over Pixels: Learning Variable-Length Visual Programs
Piotr WyrwiÅski, Kacper Dobek, Krzysztof Krawiec
Discrete visual tokenizers translate images into ordered sequences of codes, providing a natural representation for structural description of scenes. Yet existing adaptive tokenize…
QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling
Preetam Sharma, Kacper Dobek
Scalar post-training quantizers discard pairwise coordinate structure within weight rows. We introduce QAM-W (Quadrature Amplitude Modulation for Weights), a codec that recovers th…
Autoassociative Learning of Structural Representations for Modeling and Classification in Medical Imaging
Zuzanna Buchnajzer, Kacper Dobek, StanisÅaw Hapke +2
Deep learning architectures based on convolutional neural networks tend to rely on continuous, smooth features. While this characteristics provides significant robustness and prove…
Modeling Retinal Ganglion Cells with Neural Differential Equations
Kacper Dobek, Daniel Jankowski, Krzysztof Krawiec
This work explores Liquid Time-Constant Networks (LTCs) and Closed-form Continuous-time Networks (CfCs) for modeling retinal ganglion cell activity in tiger salamanders across thre…