Search Results for author:
Found 8 papers, 5 papers with code
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Representation Learning
This revealed that the driving factor behind both, the modality gap and the object bias, is the information imbalance between images and captions.
Is Mamba Capable of In-Context Learning?
State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL), a variant of meta-learning concerning the learned ability to solve tasks during a neural network forward pass, exploiting contextual information provided as input to the model.
Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
In this work, we study rapid, step-wise improvements of the loss in transformers when being confronted with multi-step decision tasks.
Latent Diffusion Counterfactual Explanations
LDCE harnesses the capabilities of recent class- or text-conditional foundation latent diffusion models to expedite counterfactual generation and focus on the important, semantic parts of the data.
Climate-sensitive Urban Planning through Optimization of Tree Placements
We show the efficacy of our approach across a wide spectrum of study areas and time scales.
Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars
In this work, we introduce a unifying search space design framework based on context-free grammars that can naturally and compactly generate expressive hierarchical search spaces that are 100s of orders of magnitude larger than common spaces from the literature.
Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
Neural architecture search (NAS) and hyperparameter optimization (HPO) make deep learning accessible to non-experts by automatically finding the architecture of the deep neural network to use and tuning the hyperparameters of the used training pipeline.
Towards Understanding Adversarial Robustness of Optical Flow Networks
We show how these mistakes can be rectified in order to make optical flow networks robust to physical patch-based attacks.
