Related papers: PixelCraft: A Multi-Agent System for High-Fidelity…
The rise of Multimodal Large Language Models (MLLMs), renowned for their advanced instruction-following and reasoning capabilities, has significantly propelled the field of visual reasoning. However, due to limitations in their image…
Understanding visual art requires reasoning across multiple perspectives -- cultural, historical, and stylistic -- beyond mere object recognition. While recent multimodal large language models (MLLMs) perform well on general image…
Large Vision-Language Models (LVLMs) have achieved significant success in multimodal tasks, with multimodal chain-of-thought (MCoT) further enhancing performance and interpretability. Recent MCoT methods fall into two categories: (i)…
The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Moreover, the unsupervised nature of this task makes it…
The rapid advancement of image generation technologies intensifies the demand for interpretable and robust detection methods. Although existing approaches often attain high accuracy, they typically operate as black boxes without providing…
Graphical User Interface (GUI) Agents, powered by multimodal large language models (MLLMs), have shown great potential for task automation on computing devices such as computers and mobile phones. However, existing agents face challenges in…
Most vision-language systems are static observers: they describe pixels, do not act, and cannot safely improve under shift. This passivity limits generalizable, physically grounded visual intelligence. Learning through action, not static…
Answering complex medical questions requires not only domain expertise and patient-specific information, but also structured and multi-perspective reasoning. Existing multi-agent approaches often rely on fixed roles or shallow interaction…
Multi-subject image generation aims to synthesize user-provided subjects in a single image while preserving subject fidelity, ensuring prompt consistency, and aligning with human aesthetic preferences. Existing In-Context-Learning based…
Vision-language models such as CLIP have shown impressive capabilities in encoding texts and images into aligned embeddings, enabling the retrieval of multimodal data in a shared embedding space. However, these embedding-based models still…
Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents.…
Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs), including recognizing key information from visual inputs and conducting reasoning over it. While fine-tuning MLLMs for…
Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference.…
Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted…
While Multimodal Large Language Models (MLLMs) excel at visual understanding, they often struggle in complex scenarios that require visual planning and imagination. Inspired by how humans use sketching as a form of visual thinking to…
There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-based planning, provides flexibility in problem solving and…
Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in…
Large language models (LLMs) show strong reasoning via chain-of-thought (CoT) prompting, but the process is opaque, which makes verification, debugging, and control difficult in high-stakes settings. We present Vis-CoT, a human-in-the-loop…
Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale (>30B) models or collapse when downsized to…
Recent advances in large Vision-Language Models (VLMs) have exhibited strong reasoning capabilities on complex visual tasks by thinking with images in their Chain-of-Thought (CoT), which is achieved by actively invoking tools to analyze…