Search Results for author:
Found 7 papers, 5 papers with code
Multi-Modal Hallucination Control by Visual Information Grounding
In particular, we show that as more tokens are generated, the reliance on the visual prompt decreases, and this behavior strongly correlates with the emergence of hallucinations.
A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data
We find that the backward diffusion process acting after a time $t$ is governed by a phase transition at some threshold time, where the probability of reconstructing high-level features, like the class of an image, suddenly drops.
How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model
The model is a classification task where each class corresponds to a group of high-level features, chosen among several equivalent groups associated with the same class.
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space: By adding the fine-tuned weights of different tasks, the model's performance can be improved on these tasks, while negating them leads to task forgetting.
What Can Be Learnt With Wide Convolutional Neural Networks?
Interestingly, we find that, despite their hierarchical structure, the functions generated by infinitely-wide deep CNNs are too rich to be efficiently learnable in high dimension.
Locality defeats the curse of dimensionality in convolutional teacher-student scenarios
Convolutional neural networks perform a local and translationally-invariant treatment of the data: quantifying which of these two aspects is central to their success remains a challenge.
Relative stability toward diffeomorphisms indicates performance in deep nets
Understanding why deep nets can classify data in large dimensions remains a challenge.
