Related papers: Probing and Inducing Combinational Creativity in V…

With the emergence of large language models (LLMs) and vision foundation models, how to combine the intelligence and capacity of these open-sourced or API-available models to achieve open-world visual perception remains an open question. In…

Traditional supervised methods for detecting AI-generated images depend on large, curated datasets for training and fail to generalize to novel, out-of-domain image generators. As an alternative, we explore pre-trained Vision-Language…

Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific…

Visual reasoning (VR), which is crucial in many fields for enabling human-like visual understanding, remains highly challenging. Recently, compositional visual reasoning approaches, which leverage the reasoning abilities of large language…

This work investigates a challenging task named open-domain interleaved image-text generation, which generates interleaved texts and images following an input query. We propose a new interleaved generation framework based on prompting…

The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a novel framework with textual embeddings from Pre-trained…

The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding…

We introduce MAIA (Multimodal AI Assessment), a native-Italian benchmark designed for fine-grained investigation of the reasoning abilities of visual language models on videos. MAIA differs from other available video benchmarks for its…

As an emergent process, creativity relies on explorations via sampling and prototyping for problem construction. These activities compile knowledge, provide a context enveloping the solution, and answer questions. With Generative AI,…

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Vision-Language Models (VLMs) building upon the foundation of powerful large language models have made rapid progress in reasoning across visual and textual data. While VLMs perform well on vision tasks that they are trained on, our results…

One of the defining characteristics of human creativity is the ability to make conceptual leaps, creating something surprising from typical knowledge. In comparison, deep neural networks often struggle to handle cases outside of their…

Solving complex visual tasks such as "Who invented the musical instrument on the right?" involves a composition of skills: understanding space, recognizing instruments, and also retrieving prior knowledge. Recent work shows promise by…

Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I), whether instantiated as assembled unified frameworks which couple powerful vision-language model (VLM) with…

The advancement of large language models (LLMs) has catalyzed a paradigm shift from code generation assistance to autonomous coding agents, enabling a novel development methodology termed "Vibe Coding" where developers validate AI-generated…

Recent text-to-image generative models have enabled us to transform our words into vibrant, captivating imagery. The surge of personalization techniques that has followed has also allowed us to imagine unique concepts in new scenes.…

In cognitive science and AI, a longstanding question is whether machines learn representations that align with those of the human mind. While current models show promise, it remains an open question whether this alignment is superficial or…

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across multi-modal tasks by scaling model size and training data. However, these dense LVLMs incur significant computational costs and motivate the exploration of…

In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information. The dominant connector-based paradigm projects visual…

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations,…