相关论文: Z-LaVI: Zero-Shot Language Solver Fueled by Visual…

Recent advancements in zero-shot commonsense reasoning have empowered Pre-trained Language Models (PLMs) to acquire extensive commonsense knowledge without requiring task-specific fine-tuning. Despite this progress, these models frequently…

Recent approaches to zero-shot commonsense reasoning have enabled Pre-trained Language Models (PLMs) to learn a broad range of commonsense knowledge without being tailored to specific situations. However, they often suffer from human…

Aligning the recent large language models (LLMs) with computer vision models leads to large vision-language models (LVLMs), which have paved the way for zero-shot image reasoning tasks. However, LVLMs are usually trained on short high-level…

The potential of Vision-Language Models (VLMs) often remains underutilized in handling complex text-based problems, particularly when these problems could benefit from visual representation. Resonating with humans' ability to solve complex…

Vision-language models (VLMs) are often deployed on text-only inputs, although they are trained with images. We find that removing the vision modality causes large drops in accuracy and severe miscalibration, and the model does not behave…

Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-to-text retrieval. However, such performance does not realize in tasks that require a finer-grained correspondence…

Vision-language models (VLMs) are impactful in part because they can be applied to a variety of visual understanding tasks in a zero-shot fashion, without any fine-tuning. We study $\textit{generative VLMs}$ that are trained for next-word…

Contrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data, demonstrating remarkable "zero-shot" generalization ability for various image tasks. However, how to…

Vision-language tasks, such as VQA, SNLI-VE, and VCR are challenging because they require the model's reasoning ability to understand the semantics of the visual world and natural language. Supervised methods working for vision-language…

In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories by composing known simpler concepts. However, existing vision-language models (VLMs), despite achieving significant progress…

We propose LENS, a modular approach for tackling computer vision problems by leveraging the power of large language models (LLMs). Our system uses a language model to reason over outputs from a set of independent and highly descriptive…

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…

Language-vision models like CLIP have made significant strides in vision tasks, such as zero-shot image classification (ZSIC). However, generating specific and expressive visual descriptions remains challenging; descriptions produced by…

We explore the extent to which zero-shot vision-language models exhibit gender bias for different vision tasks. Vision models traditionally required task-specific labels for representing concepts, as well as finetuning; zero-shot models…

Latent visual reasoning aims to mimic human's imagination process by meditating through hidden states of Multimodal Large Language Models. While recognized as a promising paradigm for visual reasoning, the underlying mechanisms driving its…

Large language models have demonstrated robust performance on various language tasks using zero-shot or few-shot learning paradigms. While being actively researched, multimodal models that can additionally handle images as input have yet to…

Vision-language models (VLMs) have demonstrated remarkable potential in integrating visual and linguistic information, but their performance is often constrained by the need for extensive, high-quality image-text training data. Curation of…

Vision-language models (VLMs) embed aligned image-text pairs into a joint space but often rely on deterministic embeddings, assuming a one-to-one correspondence between images and texts. This oversimplifies real-world relationships, which…

Large Language Models (LLMs) demonstrate impressive reasoning ability and the maintenance of world knowledge not only in natural language tasks, but also in some vision-language tasks such as open-domain knowledge-based visual question…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…