Related papers: Look on Demand: A Cognitive Scheduling Framework f…

Humans possess spatial reasoning abilities that enable them to understand spaces through multimodal observations, such as vision and sound. Large multimodal reasoning models extend these abilities by learning to perceive and reason, showing…

Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visual component typically depends only on the instance-level…

Understanding information from a collection of multiple documents, particularly those with visually rich elements, is important for document-grounded question answering. This paper introduces VisDoMBench, the first comprehensive benchmark…

Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form…

Visual reasoning is dominated by end-to-end neural networks scaled to billions of model parameters and training examples. However, even the largest models struggle with compositional reasoning, generalization, fine-grained spatial and…

Constructing scientific multimodal document reasoning datasets for foundation model training involves an inherent trade-off among scale, faithfulness, and realism. To address this challenge, we introduce the synthesize-and-reground…

Multimodal Large Language Models (MLLMs) frequently hallucinate due to their reliance on fragile, linear reasoning and weak visual grounding. We propose Visual Attention Reasoning (VAR), a reinforcement learning framework that reformulates…

Recent advancements in Large Vision-Language Models have showcased remarkable capabilities. However, they often falter when confronted with complex reasoning tasks that humans typically address through visual aids and deliberate,…

Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.…

Multimodal Intent Recognition (MIR) aims to understand complex user intentions by leveraging text, video, and audio signals. However, existing approaches face two key challenges: (1) overlooking intricate cross-modal interactions for…

As Large Language Models (LLMs) gain expertise across diverse domains and modalities, scalable oversight becomes increasingly challenging, particularly when their capabilities may surpass human evaluators. Debate has emerged as a promising…

Recent advances in test-time optimization have led to remarkable reasoning capabilities in Large Language Models (LLMs), enabling them to solve highly complex problems in math and coding. However, the reasoning capabilities of multimodal…

Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only…

Integrating visual and linguistic information into a single multimodal representation is an unsolved problem with wide-reaching applications to both natural language processing and computer vision. In this paper, we present a simple method…

The "style trap" poses a significant challenge for Large Vision-Language Models (LVLMs), hindering robust semantic understanding across diverse visual styles, especially in in-context learning (ICL). Existing methods often fail to…

We propose a new spatial memory module and a spatial reasoner for the Visual Grounding (VG) task. The goal of this task is to find a certain object in an image based on a given textual query. Our work focuses on integrating the regions of a…

Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent…

Multimodal representation learning has been largely driven by contrastive models such as CLIP, which learn a shared embedding space by aligning paired image-text samples. While effective for general-purpose representation learning, such…

Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear. We analyze reasoning dynamics in 18 VLMs covering instruction-tuned and…

Multimodal Large Language Models (MLLMs) are making significant progress in multimodal reasoning. Early approaches focus on pure text-based reasoning. More recent studies have incorporated multimodal information into the reasoning steps;…