Related papers: Does language help generalization in vision models…
Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training. By extending previous work on compositional generalization in semantic parsing, we…
How does visual information included in training affect language processing in audio- and text-based deep learning models? We explore how such visual grounding affects model-internal representations of words, and find substantially…
Image geolocalization has traditionally been addressed through retrieval-based place recognition or geometry-based visual localization pipelines. Recent advances in Vision-Language Models (VLMs) have demonstrated strong zero-shot reasoning…
Current approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word…
Generalist multimodal agents are expected to unify perception, language, and control - operating robustly across diverse real world domains. However, current evaluation practices remain fragmented across isolated benchmarks, making it…
Domain generalization aims at training on source domains to uncover a domain-invariant feature space, allowing the model to perform robust generalization ability on unknown target domains. However, due to domain gaps, it is hard to find…
In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast,…
Vision (image and video) - Language (VL) pre-training is the recent popular paradigm that achieved state-of-the-art results on multi-modal tasks like image-retrieval, video-retrieval, visual question answering etc. These models are trained…
Multimodal large language models (MLLMs) have altered the landscape of computer vision, obtaining impressive results across a wide range of tasks, especially in zero-shot settings. Unfortunately, their strong performance does not always…
Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks. Yet, the exact capabilities of these black-box models are still poorly…
In-context learning (ICL) enables Large Language Models (LLMs) to learn tasks from demonstration examples without parameter updates. Although it has been extensively studied in LLMs, its effectiveness in Vision-Language Models (VLMs)…
The objective of domain generalization (DG) is to enable models to be robust against domain shift. DG is crucial for deploying vision-language models (VLMs) in real-world applications, yet most existing methods rely on domain labels that…
Generalization is a pivotal challenge for agents following natural language instructions. To approach this goal, we leverage a vision-language model (VLM) for visual grounding and transfer its vision-language knowledge into reinforcement…
Vision-language models, which integrate computer vision and natural language processing capabilities, have demonstrated significant advancements in tasks such as image captioning and visual question and answering. However, similar to…
Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…
Vision-language fine-tuning has emerged as an efficient paradigm for constructing multimodal foundation models. While textual context often highlights semantic relationships within an image, existing fine-tuning methods typically overlook…
The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questions remain unanswered: Can CLIP generalize to an entirely…
Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods mostly focus on training 3D models using either image or…
This paper presents several novel findings on the explainability of vision reflection in large multimodal models (LMMs). First, we show that prompting an LMM to verify the prediction of a specialized vision model can improve recognition…
Recent work considered how images paired with speech can be used as supervision for building speech systems when transcriptions are not available. We ask whether visual grounding can be used for cross-lingual keyword spotting: given a text…