Related papers: What MLLMs Learn about When they Learn about Multi…

While multimodal fusion has been extensively studied in Multimodal Sentiment Analysis (MSA), the role of fusion depth and multimodal capacity allocation remains underexplored. In this work, we position fusion depth, scalability, and…

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…

Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space'' from videos? We…

As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary…

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on…

Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains less understood. We introduce "Mind's Eye", a…

The ability to process information from multiple modalities and to reason through it step-by-step remains a critical challenge in advancing artificial intelligence. However, existing reasoning benchmarks focus on text-only reasoning, or…

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based…

Large language models (LLMs) have demonstrated impressive capabilities, yet their internal mechanisms for handling reasoning-intensive tasks remain underexplored. To advance the understanding of model-internal processing mechanisms, we…

Skill composition is the ability to combine previously learned skills to solve new tasks. As neural networks acquire increasingly complex skills during their pretraining, it is not clear how successfully they can compose them. In this…

Multimodal large language models (MLLMs) combine visual and textual data for tasks such as image captioning and visual question answering. Proper uncertainty calibration is crucial, yet challenging, for reliable use in areas like healthcare…

Recent advancements in Large Vision-Language Models (LVLMs) have significantly enhanced their ability to integrate visual and linguistic information, achieving near-human proficiency in tasks like object recognition, captioning, and visual…

Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear. Existing benchmarks lack a systematic exploration of the specific tasks where…

Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…

Recent advances in large language models (LLMs) and vision-language models (LVLMs) have shown promise across many tasks, yet their scientific reasoning capabilities remain untested, particularly in multimodal settings. We present…

Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their…

Transformer-based language models, though not explicitly trained to mimic brain recordings, have demonstrated surprising alignment with brain activity. Progress in these models-through increased size, instruction-tuning, and…

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…

Logical reasoning serve as a central capability in LLMs and includes three main forms: deductive, inductive, and abductive reasoning. In this work, we study the knowledge representations of these reasoning types in LLMs and analyze the…

Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring…