Related papers: GLACIA: Instance-Aware Positional Reasoning for Gl…

Large Vision-Language Models (LVLMs) face a tug-of-war between powerful linguistic priors and visual evidence, often leading to \emph{semantic drift}: a progressive detachment from the input image that can abruptly emerge at specific…

The task of multi-image cued story generation, such as visual storytelling dataset (VIST) challenge, is to compose multiple coherent sentences from a given sequence of images. The main difficulty is how to generate image-specific sentences…

Generalized Referring expressions can describe one object, several related objects, or none at all. Existing generalized referring segmentation (GRES) models treat all cases alike, predicting a single binary mask and ignoring how linguistic…

Multimodal large language models (MLLMs) have demonstrated remarkable abilities in comprehending visual input alongside text input. Typically, these models are trained on extensive data sourced from the internet, which are sufficient for…

As large vision language models (VLMs) advance, their capabilities in multilingual visual question answering (mVQA) have significantly improved. Chain-of-thought (CoT) reasoning has been proven to enhance interpretability and complex…

Numerous decision-making tasks require estimating causal effects under interventions on different parts of a system. As practitioners consider using large language models (LLMs) to automate decisions, studying their causal reasoning…

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate steps. While CoT improves both interpretability and accuracy,…

Large language models (LLMs) have recently demonstrated strong reasoning capabilities and attracted increasing research attention in the field of autonomous driving (AD). However, safe application of LLMs on AD perception and prediction…

Integrating large language models (LLMs) with knowledge graphs derived from domain-specific data represents an important advancement towards more powerful and factual reasoning. As these models grow more capable, it is crucial to enable…

The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation. In this paper, we apply graph convolution into the semantic segmentation task…

Most recent 3D instance segmentation methods are open vocabulary, offering a greater flexibility than closed-vocabulary methods. Yet, they are limited to reasoning within a specific set of concepts, \ie the vocabulary, prompted by the user…

Large foundation models enable powerful reasoning for autonomous systems, but mapping semantic intent to reliable real-time control remains challenging. Existing approaches either (i) let Large Language Models (LLMs) generate trajectories…

Disruptions at critical logistics nodes pose severe risks to global supply chains, yet existing risk prediction systems typically prioritize forecasting accuracy without providing operationally interpretable early warnings. This paper…

The integration of Large Language Models (LLMs) with computer vision is profoundly transforming perception tasks like image segmentation. For intelligent transportation systems (ITS), where accurate scene understanding is critical for…

When a multimodal Transformer answers a visual question, is the prediction driven by visual evidence, linguistic reasoning, or genuinely fused cross-modal computation -- and how does this structure evolve across layers? We address this…

Multimodal intelligence development recently show strong progress in visual understanding and high level reasoning. Though, most reasoning system still reply on textual information as the main medium for inference. This limit their…

In-context learning (ICL) in large language models (LLMs) is a striking phenomenon, yet its underlying mechanisms remain only partially understood. Previous work connects linear self-attention (LSA) to gradient descent (GD), this connection…

Vision-Language-Action (VLA) models have demonstrated strong potential for predicting semantic actions in navigation tasks, demonstrating the ability to reason over complex linguistic instructions and visual contexts. However, they are…

Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations…

While Multimodal Large Language Models (MLLMs) excel at visual understanding tasks through text reasoning, they often fall short in scenarios requiring visual imagination. Unlike current works that take predefined external toolkits or…