相关论文: MAtch, eXpand and Improve: Unsupervised Finetuning…

The exponential growth of large language models (LLMs) has opened up numerous possibilities for multimodal AGI systems. However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal…

Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…

In-line with the success of deep learning on traditional recognition problem, several end-to-end deep models for zero-shot recognition have been proposed in the literature. These models are successful to predict a single unseen label given…

Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data. Recently, self-supervised learning of speech representation…

Visual storytelling is an emerging field that combines images and narratives to create engaging and contextually rich stories. Despite its potential, generating coherent and emotionally resonant visual stories remains challenging due to the…

Low-shot image classification, where training images are limited or inaccessible, has benefited from recent progress on pre-trained vision-language (VL) models with strong generalizability, e.g. CLIP. Prompt learning methods built with VL…

Reinforcement learning based post-training paradigms for Video Large Language Models (VideoLLMs) have achieved significant success by optimizing for visual-semantic tasks such as captioning or VideoQA. However, while these approaches…

Foundational Vision-Language Models (VLMs) excel across diverse tasks, but adapting them to new domains without forgetting prior knowledge remains a critical challenge. Continual Learning (CL) addresses this challenge by enabling models to…

Training or finetuning large-scale language models (LLMs) requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks. One approach is to treat these models as black…

Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…

In this paper, we leverage large language models (LMs) to perform zero-shot text style transfer. We present a prompting method that we call augmented zero-shot learning, which frames style transfer as a sentence rewriting task and requires…

Large language models (LLMs) have emerged as powerful general-purpose interfaces for many machine learning problems. Recent work has adapted LLMs to generative visual tasks like image captioning, visual question answering, and visual chat,…

This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used…

Training or finetuning large-scale language models (LLMs) such as GPT-3 requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks. One practical area of research is…

We tackle the problem of zero-shot cross-lingual transfer in NLP tasks via the use of language adapters (LAs). Most of the earlier works have explored training with adapter of a single source (often English), and testing either using the…

Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to a laborious and time-consuming visual recognition…

Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

We present a new method to learn video representations from unlabeled data. Given large-scale unlabeled video data, the objective is to benefit from such data by learning a generic and transferable representation space that can be directly…

Zero-shot learning (ZL) is crucial for tasks involving unseen categories, such as natural language processing, image classification, and cross-lingual transfer.Current applications often fail to accurately infer and handle new relations…