Related papers: Exploring Contur beyond its default mode: a case s…
Contrastive self-supervised learning has been successfully used in many domains, such as images, texts, graphs, etc., to learn features without requiring label information. In this paper, we propose a new local contrastive feature learning…
Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…
Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to the enhanced and preferential processing given relevant stimuli. On the contrary,…
A statistical learning/inference framework for color demosaicing is presented. We start with simplistic assumptions about color constancy, and recast color demosaicing as a blind linear inverse problem: color parameterizes the unknown…
Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an…
Understanding which inductive biases could be helpful for the unsupervised learning of object-centric representations of natural scenes is challenging. In this paper, we systematically investigate the performance of two models on datasets…
Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of…
Deep learning methods employ multiple processing layers to learn hierarchical representations of data and have produced state-of-the-art results in many domains. Recently, a variety of model designs and methods have blossomed in the context…
Training autoregressive models to better predict under the test metric, instead of maximizing the likelihood, has been reported to be beneficial in several use cases but brings additional complications, which prevent wider adoption. In this…
Additionally, the strong dependency among in-context examples makes it an NP-hard combinatorial optimization problem and enumerating all permutations is infeasible. Hence we propose LENS, a fiLter-thEN-Search method to tackle this challenge…
Language-based colorization produces plausible and visually pleasing colors under the guidance of user-friendly natural language descriptions. Previous methods implicitly assume that users provide comprehensive color descriptions for most…
The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that these pre-trained representations do encode some level of…
Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination -- generating content ungrounded in the realities of training data. Recent work has focused on decoding techniques to improve…
Language models (LMs) trained on raw texts have no direct access to the physical world. Gordon and Van Durme (2013) point out that LMs can thus suffer from reporting bias: texts rarely report on common facts, instead focusing on the unusual…
Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…
We study the intrinsic transformation of feature maps across convolutional network layers with explicit top-down control. To this end, we develop top-down feature transformer (TFT), under controllable parameters, that are able to account…
Chain-of-thought (CoT) reasoning has exhibited impressive performance in language models for solving complex tasks and answering questions. However, many real-world questions require multi-modal information, such as text and images.…
Language models, characterized by their black-box nature, often hallucinate and display sensitivity to input perturbations, causing concerns about trust. To enhance trust, it is imperative to gain a comprehensive understanding of the…
Machine learning based on convolutional neural networks can be used to study jet images from the LHC. Top tagging in fat jets offers a well-defined framework to establish our DeepTop approach and compare its performance to QCD-based top…
We develop a geometric account of sequence modelling that links patterns in the data to measurable properties of the loss landscape in transformer networks. First, we cast conditional sequence distributions into a Hilbert-space framework…