Related papers: CRIT: Graph-Based Automatic Data Synthesis to Enha…

Vision-language models (VLMs) have demonstrated strong reasoning abilities in literal multimodal tasks such as visual mathematics and science question answering. However, figurative language, such as sarcasm, humor, and metaphor, remains a…

As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce MERLOT, a model that learns multimodal script knowledge by…

Multi-Modal Large Language Models (MLLMs) have demonstrated impressive performance in various VQA tasks. However, they often lack interpretability and struggle with complex visual inputs, especially when the resolution of the input image is…

Spatial reasoning has emerged as a critical capability for Multimodal Large Language Models (MLLMs), drawing increasing attention and rapid advancement. However, existing benchmarks primarily focus on single-step perception-to-judgment…

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies…

Complex reasoning problems often involve implicit spatial and geometric relationships that are not explicitly encoded in text. While recent reasoning models perform well across many domains, purely text-based reasoning struggles to capture…

Chain-of-thought (CoT) reasoning has exhibited impressive performance in language models for solving complex tasks and answering questions. However, many real-world questions require multi-modal information, such as text and images.…

Composed Image Retrieval (CIR) is the task of retrieving a target image from a gallery using a composed query consisting of a reference image and a modification text. Among various CIR approaches, training-free zero-shot methods based on…

Evaluations of large language models (LLMs) primarily emphasize convergent logical reasoning, where success is defined by producing a single correct proof. However, many real-world reasoning problems admit multiple valid derivations,…

The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in actual visual evidence. However, existing datasets face limitations in scalability due to…

Multimodal large language models (LLMs) have made rapid progress in visual understanding, yet their extension from images to videos often reduces to a naive concatenation of frame tokens. In this work, we investigate what video finetuning…

Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation, where reliability requires grounding model outputs in heterogeneous input sources and verifying…

Recent deep research systems have improved the ability of large language models to produce long, grounded reports through iterative retrieval and reasoning. However, most text-centered systems rely mainly on textual evidence, while…

With the aim of detecting AI-generated images and identifying the specific models responsible for their generation, we propose a multi-modal multi-task model. The model leverages pre-trained BERT and CLIP Vision encoders for text and image…

Vision-language models (VLMs) like CLIP have been cherished for their ability to perform zero-shot visual recognition on open-vocabulary concepts. This is achieved by selecting the object category whose textual representation bears the…

Pretraining robust vision or multimodal foundation models (e.g., CLIP) relies on large-scale datasets that may be noisy, potentially misaligned, and have long-tail distributions. Previous works have shown promising results in augmenting…

Humans construct internal world models and reason by manipulating the concepts within these models. Recent advances in AI, particularly chain-of-thought (CoT) reasoning, approximate such human cognitive abilities, where world models are…

The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often…

Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, question answering, etc. Although existing multimodal models present impressive…

Spatial reasoning from monocular images is essential for autonomous driving, yet current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception, particularly under large scale variation and ambiguous object…