Related papers: MAGMA-Edu: Multi-Agent Generative Multimodal Frame…

Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image show emerging abilities to reason over multiple related…

Multimodal Large Language Models (MLLMs) have significantly advanced vision-language understanding. However, even state-of-the-art models struggle with geometric reasoning, revealing a critical bottleneck: the extreme scarcity of…

Despite their remarkable capabilities, large language models (LLMs) often produce responses containing factual inaccuracies due to their sole reliance on the parametric knowledge they encapsulate. Retrieval-Augmented Generation (RAG), an ad…

In virtual reality (VR) educational scenarios, Pedagogical agents (PAs) enhance immersive learning through realistic appearances and interactive behaviors. However, most existing PAs rely on static speech and simple gestures. This…

Large language models (LLMs) are increasingly deployed as conversational tutors in STEM education, yet most systems still rely on a single LLM with a static retrieval-augmented generation (RAG) pipeline over course materials. This design…

While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image reasoning scenarios. Multi-image reasoning presents fundamental challenges including complex…

In this paper, we introduce knowledge image generation as a new task, alongside the Massive Multi-Discipline Multi-Tier Knowledge-Image Generation Benchmark (MMMG) to probe the reasoning capability of image generation models. Knowledge…

Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to…

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,…

Virtual Labs offer valuable opportunities for hands-on, inquiry-based science learning, yet teachers often struggle to adapt them to fit their instructional goals. Third-party materials may not align with classroom needs, and developing…

Despite their popularity and success, Multimodal Large Language Models (MLLMs) often struggle to interpret images accurately, which limits their reasoning capability in complex scenarios (e.g., high object density and complex background…

Recently, unified multimodal models (UMMs) have made remarkable progress in integrating visual understanding and generation, demonstrating strong potential for complex text-to-image (T2I) tasks. Despite their theoretical promise, a…

Text-to-video generation models have shown significant progress in the recent years. However, they still struggle with generating complex dynamic scenes based on compositional text prompts, such as attribute binding for multiple objects,…

Designing good reflection questions is pedagogically important but time-consuming and unevenly supported across teachers. This paper introduces a reflection-in-reflection framework for automated generation of reflection questions with large…

Recent advances in Retrieval-Augmented Generation (RAG) have significantly improved response accuracy and relevance by incorporating external knowledge into Large Language Models (LLMs). However, existing RAG methods primarily focus on…

While advancements in Text-to-Video (T2V) generative AI offer a promising path toward democratizing content creation, current models are often optimized for visual fidelity rather than instructional efficacy. This study introduces…

Large Language Model (LLM) agent systems have advanced rapidly, driven by their strong generalization in zero-shot settings. To further enhance reasoning and accuracy on complex tasks, Multi-Agent Debate (MAD) has emerged as a promising…

Multimodality-to-Multiaudio (MM2MA) generation faces significant challenges in synthesizing diverse and contextually aligned audio types (e.g., sound effects, speech, music, and songs) from multimodal inputs (e.g., video, text, images),…

Simulated Students offer a valuable methodological framework for evaluating pedagogical approaches and modelling diverse learner profiles, tasks which are otherwise challenging to undertake systematically in real-world settings. Recent…

As Vision-Language Models (VLMs) become integral to educational decision-making, ensuring their fairness is paramount. However, current text-centric evaluations neglect the visual modality, leaving an unregulated channel for latent social…