Search Results for author:
Found 8 papers, 1 papers with code
IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic Representations
Current foundation models exhibit impressive capabilities when prompted either with text only or with both image and text inputs.
Simplicity Bias of Transformers to Learn Low Sensitivity Functions
Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of the inductive biases that they have and how those biases are different from other neural network architectures remains elusive.
DeLLMa: A Framework for Decision Making Under Uncertainty with Large Language Models
Large language models (LLMs) are increasingly used across society, including in domains like business, engineering, and medicine.
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback
Then, it uses two VLMs to select the best generation: a Visual Question Answering model that measures the alignment of generated images to the text, and another that measures the generation's aesthetic quality.
Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models
In this paper, we instead demonstrate that Transformers learn to implement higher-order optimization methods to perform ICL.
SCENE: Self-Labeled Counterfactuals for Extrapolating to Negative Examples
In this work, we propose Self-labeled Counterfactuals for Extrapolating to Negative Examples (SCENE), an automatic method for synthesizing training data that greatly improves models' ability to detect challenging negative examples.
Topological Regularization for Dense Prediction
Dense prediction tasks such as depth perception and semantic segmentation are important applications in computer vision that have a concrete topological description in terms of partitioning an image into connected components or estimating a function with a small number of local extrema corresponding to objects in the image.
Harnessing the Conditioning Sensorium for Improved Image Translation
Multi-modal domain translation typically refers to synthesizing a novel image that inherits certain localized attributes from a 'content' image (e. g. layout, semantics, or geometry), and inherits everything else (e. g. texture, lighting, sometimes even semantics) from a 'style' image.
