相关论文: Does Vision-and-Language Pretraining Improve Lexic…

Visual and linguistic pre-training aims to learn vision and language representations together, which can be transferred to visual-linguistic downstream tasks. However, there exists semantic confusion between language and vision during the…

Current Vision-and-Language Navigation (VLN) tasks mainly employ textual instructions to guide agents. However, being inherently abstract, the same textual instruction can be associated with different visual signals, causing severe…

Existing Large Vision-Language Models (LVLMs) excel at matching concepts across multi-modal inputs but struggle with compositional concepts and high-level relationships between entities. This paper introduces Progressive multi-granular…

Commonsense reasoning often requires both textual and visual knowledge, yet Large Language Models (LLMs) trained solely on text lack visual grounding (e.g., "what color is an emperor penguin's belly?"). Visual Language Models (VLMs) perform…

This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering)…

Visual grounding of Language aims at enriching textual representations of language with multiple sources of visual knowledge such as images and videos. Although visual grounding is an area of intense research, inter-lingual aspects of…

Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In…

As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large vision-language models (LVLMs). However, existing methods…

Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence…

Pre-trained language models are still far from human performance in tasks that need understanding of properties (e.g. appearance, measurable quantity) and affordances of everyday objects in the real world since the text lacks such…

Many vision-language models (VLMs) that prove very effective at a range of multimodal task, build on CLIP-based vision encoders, which are known to have various limitations. We investigate the hypothesis that the strong language backbone in…

When thinking with images, humans rarely rely on a single glance: they revisit visual evidence while reasoning. In contrast, most Multimodal Language Models encode an image once to key-value cache and then reason purely in text, making it…

This paper explores training medical vision-language models (VLMs) -- where the visual and language inputs are embedded into a common space -- with a particular focus on scenarios where training data is limited, as is often the case in…

Visual grounding refers to the ability of a model to identify a region within some visual input that matches a textual description. Consequently, a model equipped with visual grounding capabilities can target a wide range of applications in…

Large-scale multimodal representation learning successfully optimizes for zero-shot transfer at test time. Yet the standard pretraining paradigm (contrastive learning on large amounts of image-text data) does not explicitly encourage…

Compared to image-text pair data, interleaved corpora enable Vision-Language Models (VLMs) to understand the world more naturally like humans. However, such existing datasets are crawled from webpage, facing challenges like low knowledge…

Vision-language models (VLMs) have advanced rapidly in processing multimodal information, but their ability to reconcile conflicting signals across modalities remains underexplored. This work investigates how VLMs process ASCII art, a…

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared…

With the recent progress in large-scale vision and language representation learning, Vision Language Pre-training (VLP) models have achieved promising improvements on various multi-modal downstream tasks. Albeit powerful, these models have…