相关论文: CoLLIE: Continual Learning of Language Grounding f…

Large language-vision models (LVLMs) such as CLIP, Flamingo, and BLIP have revolutionized AI by enabling understanding across textual and visual modalities. These models excel at tasks like image captioning, visual question answering, and…

Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption datasets. Our work…

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of…

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

We address the problem of phrase grounding by lear ing a multi-level common semantic space shared by the textual and visual modalities. We exploit multiple levels of feature maps of a Deep Convolutional Neural Network, as well as…

A fundamental question in cognitive science and AI concerns whether different learning modalities: language, vision, and action, give rise to distinct or shared internal representations. Traditional views assume that models trained on…

Multimodal Large Language Models (MLLMs) have demonstrated a wide range of capabilities across many domains, including Embodied AI. In this work, we study how to best ground a MLLM into different embodiments and their associated action…

Continual learning (CL) enables models to adapt to evolving data streams without catastrophic forgetting, a fundamental requirement for real-world AI systems. However, the current methods often depend on large replay buffers or heavily…

Large language models excel at a wide range of complex tasks. However, enabling general inference in the real world, e.g., for robotics problems, raises the challenge of grounding. We propose embodied language models to directly incorporate…

Large language models (LLMs) have proven their remarkable versatility in handling a comprehensive range of language-centric applications. To expand LLMs' capabilities to a broader spectrum of modal inputs, multimodal large language models…

We introduce a novel method for multilingual transfer that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. While contextual embeddings have been shown to yield richer representations of meaning compared to their…

Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that uses the vast…

Pretrained language models for code token embeddings are used in code search, code clone detection, and other code-related tasks. Similarly, code function embeddings are useful in such tasks. However, there are no out-of-box models for…

Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…

Cognitive grammar suggests that the acquisition of language grammar is grounded within visual structures. While grammar is an essential representation of natural language, it also exists ubiquitously in vision to represent the hierarchical…

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in…

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…

Recent generalist vision-language models (VLMs) have demonstrated impressive reasoning capabilities across diverse multimodal tasks. However, these models still struggle with fine-grained object-level understanding and grounding. In terms…