🏢 Technical University of Munich

This paper presents a novel framework for achieving tighter differential privacy guarantees via mechanism-specific amplification using subsampling.

Adaptive experiment design optimizes indirect experiments in complex systems by sequentially narrowing the gap between upper and lower bounds on a targeted query, providing more efficient and informat…

Spatio-Spectral GNNs synergistically combine spatial and spectral graph filters for efficient, global information propagation, overcoming limitations of existing methods.

Open-source LLMs are vulnerable to embedding space attacks, which efficiently bypass safety mechanisms and enable data extraction, even after unlearning.

ReNO: Boost one-step text-to-image models by cleverly optimizing initial noise using reward signals, achieving state-of-the-art results efficiently.

Neural Pfaffians revolutionize many-electron Schrödinger equation solutions by using fully learnable neural wave functions based on Pfaffians, achieving unprecedented accuracy and generalizability acr…

MotionTTT: Deep learning enables accurate 3D motion-corrected MRI by cleverly estimating motion parameters during test-time training, significantly improving image reconstruction.

Boost RL efficiency in continuous action spaces by masking irrelevant actions using three novel continuous action masking methods!

GEBM: a novel graph-based energy model for robust GNN uncertainty estimation.

Drift-Resilient TabPFN masters temporal data shifts!

DiCuRL uses diffusion models to generate challenging yet achievable RL training curricula, outperforming nine state-of-the-art methods.

Coherent 3D scenes are diffused from a single RGB image using a novel image-conditioned 3D scene diffusion model, surpassing state-of-the-art methods.