Imagine observing someone scratching their arm; to understand why, additional context would be necessary. However, spotting a mosquito nearby would immediately offer a likely explanation for the person's discomfort, thereby alleviating the need for further information. This example illustrates how subtle visual cues can challenge our cognitive skills and demonstrates the complexity of interpreting visual scenarios. To study these skills, we present Visual Riddles, a benchmark aimed to test vision and language models on visual riddles requiring commonsense and world knowledge. The benchmark comprises 400 visual riddles, each featuring a unique image created by a variety of text-to-image models, question, ground-truth answer, textual hint, and attribution. Human evaluation reveals that existing models lag significantly behind human performance, which is at 82% accuracy, with Gemini-Pro-1.5 leading with 40% accuracy. Our benchmark comes with automatic evaluation tasks to make assessment scalable. These findings underscore the potential of Visual Riddles as a valuable resource for enhancing vision and language models' capabilities in interpreting complex visual scenarios. Data, code, and leaderboard are available at https://visual-riddles.github.io/.

Recent studies show that deep vision-only and language-only models--trained on disjoint modalities--nonetheless project their inputs into a partially aligned representational space. Yet we still lack a clear picture of where in each network this convergence emerges, what visual or linguistic cues support it, whether it captures human preferences in many-to-many image-text scenarios, and how aggregating exemplars of the same concept affects alignment. Here, we systematically investigate these questions. We find that alignment peaks in mid-to-late layers of both model types, reflecting a shift from modality-specific to conceptually shared representations. This alignment is robust to appearance-only changes but collapses when semantics are altered (e.g., object removal or word-order scrambling), highlighting that the shared code is truly semantic. Moving beyond the one-to-one image-caption paradigm, a forced-choice "Pick-a-Pic" task shows that human preferences for image-caption matches are mirrored in the embedding spaces across all vision-language model pairs. This pattern holds bidirectionally when multiple captions correspond to a single image, demonstrating that models capture fine-grained semantic distinctions akin to human judgments. Surprisingly, averaging embeddings across exemplars amplifies alignment rather than blurring detail. Together, our results demonstrate that unimodal networks converge on a shared semantic code that aligns with human judgments and strengthens with exemplar aggregation.

Imagine observing someone scratching their arm; to understand why, additional context would be necessary. However, spotting a mosquito nearby would immediately offer a likely explanation for the person's discomfort, thereby alleviating the need for further information. This example illustrates how subtle visual cues can challenge our cognitive skills and demonstrates the complexity of interpreting visual scenarios. To study these skills, we present Visual Riddles, a benchmark aimed to test vision and language models on visual riddles requiring commonsense and world knowledge. The benchmark comprises 400 visual riddles, each featuring a unique image created by a variety of text-to-image models, question, ground-truth answer, textual hint, and attribution.

The platonic representation hypothesis suggests that vision and language embeddings become more homogeneous as model and dataset sizes increase. In particular, pairwise distances within each modality become more similar. This suggests that as foundation models mature, it may become possible to match vision and language embeddings in a fully unsupervised fashion, i.e. without parallel data. We present the first feasibility study, and investigate conformity of existing vision and language foundation models in the context of unsupervised, or "blind", matching. First, we formulate unsupervised matching as a quadratic assignment problem and introduce a novel heuristic that outperforms previous solvers. We also develop a technique to find optimal matching problems, for which a non-trivial match is very likely. Second, we conduct an extensive study deploying a range of vision and language models on four datasets. Our analysis reveals that for many problem instances, vision and language representations can be indeed matched without supervision. This finding opens up the exciting possibility of embedding semantic knowledge into other modalities virtually annotation-free. As a proof of concept, we showcase an unsupervised classifier, which achieves non-trivial classification accuracy without any image-text annotation.

Vision Language Models excel in handling a wide range of complex tasks, including Optical Character Recognition (OCR), Visual Question Answering (VQA), and advanced geometric reasoning. However, these models fail to perform well on low-level basic visual tasks which are especially easy for humans. Our goal in this work was to determine if these models are truly "blind" to geometric reasoning or if there are ways to enhance their capabilities in this area. Our work presents a novel automatic pipeline designed to extract key information from images in response to specific questions. Instead of just relying on direct VQA, we use question-derived keywords to create a caption that highlights important details in the image related to the question. This caption is then used by a language model to provide a precise answer to the question without requiring external fine-tuning.

Recently, vision-language instruct-tuning models have made significant progress due to their more comprehensive understanding of the world. In this work, we discovered that large-scale 3D parallel training on those models leads to an imbalanced computation load across different devices. The vision and language parts are inherently heterogeneous: their data distribution and model architecture differ significantly, which affects distributed training efficiency. We rebalanced the computational loads from data, model, and memory perspectives to address this issue, achieving more balanced computation across devices. These three components are not independent but are closely connected, forming an omniverse balanced training framework. Specifically, for the data, we grouped instances into new balanced mini-batches within and across devices. For the model, we employed a search-based method to achieve a more balanced partitioning. For memory optimization, we adaptively adjusted the re-computation strategy for each partition to utilize the available memory fully. We conducted extensive experiments to validate the effectiveness of our method. Compared with the open-source training code of InternVL-Chat, we significantly reduced GPU days, achieving about 1.8x speed-up. Our method's efficacy and generalizability were further demonstrated across various models and datasets. Codes will be released at https://github.com/ModelTC/OmniBal.

Human beings perceive the world through diverse senses such as sight, smell, hearing, and touch. Similarly, multimodal large language models (MLLMs) enhance the capabilities of traditional large language models by integrating and processing data from multiple modalities including text, vision, audio, video, and 3D environments. Data plays a pivotal role in the development and refinement of these models. In this survey, we comprehensively review the literature on MLLMs from a data-centric perspective. Specifically, we explore methods for preparing multimodal data during the pretraining and adaptation phases of MLLMs. Additionally, we analyze the evaluation methods for datasets and review benchmarks for evaluating MLLMs. Our survey also outlines potential future research directions. This work aims to provide researchers with a detailed understanding of the data-driven aspects of MLLMs, fostering further exploration and innovation in this field.

Recent advancements in Computer Assisted Diagnosis have shown promising performance in medical imaging tasks, particularly in chest X-ray analysis. However, the interaction between these models and radiologists has been primarily limited to input images. This work proposes a novel approach to enhance human-computer interaction in chest X-ray analysis using Vision-Language Models (VLMs) enhanced with radiologists' attention by incorporating eye gaze data alongside textual prompts. Our approach leverages heatmaps generated from eye gaze data, overlaying them onto medical images to highlight areas of intense radiologist's focus during chest X-ray evaluation. We evaluate this methodology in tasks such as visual question answering, chest X-ray report automation, error detection, and differential diagnosis. Our results demonstrate the inclusion of eye gaze information significantly enhances the accuracy of chest X-ray analysis. Also, the impact of eye gaze on fine-tuning was confirmed as it outperformed other medical VLMs in all tasks except visual question answering. This work marks the potential of leveraging both the VLM's capabilities and the radiologist's domain knowledge to improve the capabilities of AI models in medical imaging, paving a novel way for Computer Assisted Diagnosis with a human-centred AI.

This paper introduces the ColorSwap dataset, designed to assess and improve the proficiency of multimodal models in matching objects with their colors. The dataset is comprised of 2,000 unique image-caption pairs, grouped into 1,000 examples. Each example includes a caption-image pair, along with a ``color-swapped'' pair. We follow the Winoground schema: the two captions in an example have the same words, but the color words have been rearranged to modify different objects. The dataset was created through a novel blend of automated caption and image generation with humans in the loop. We evaluate image-text matching (ITM) and visual language models (VLMs) and find that even the latest ones are still not robust at this task. GPT-4V and LLaVA score 72% and 42% on our main VLM metric, although they may improve with more advanced prompting techniques. On the main ITM metric, contrastive models such as CLIP and SigLIP perform close to chance (at 12% and 30%, respectively), although the non-contrastive BLIP ITM model is stronger (87%). We also find that finetuning on fewer than 2,000 examples yields significant performance gains on this out-of-distribution word-order understanding task. The dataset is here: https://github.com/Top34051/colorswap.

Key to tasks that require reasoning about natural language in visual contexts is grounding words and phrases to image regions. However, observing this grounding in contemporary models is complex, even if it is generally expected to take place if the task is addressed in a way that is conductive to generalization. We propose a framework to jointly study task performance and phrase grounding, and propose three benchmarks to study the relation between the two. Our results show that contemporary models demonstrate inconsistency between their ability to ground phrases and solve tasks. We show how this can be addressed through brute-force training on ground phrasing annotations, and analyze the dynamics it creates. Code and at available at https://github.com/lil-lab/phrase_grounding.