5 papers
GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models
Chaoxiang Cai, Minghe Weng, Jie Li +4
With the increase in model parameters and training data, the instruction following and generalization capabilities of Large VisionLanguage Models (LVLMs) have been significantly im…
Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
Yibo Jiang, Tao Wu, Rui Jiang +4
Unified Multimodal Models (UMMs) aim to integrate visual understanding and generation within a single structure. However, these models exhibit a notable capability mismatch, where…
SpatialText: A Pure-Text Cognitive Benchmark for Spatial Understanding in Large Language Models
Peiyao Jiang, Zequn Qin, Xi Li
Genuine spatial reasoning relies on the capacity to construct and manipulate coherent internal spatial representations, often conceptualized as mental models, rather than merely pr…
MultiCrafter: High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference Alignment
Tao Wu, Yibo Jiang, Yehao Lu +4
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 a…
OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds
Longrong Yang, Zhixiong Zeng, Yufeng Zhong +7
Multimodal large language models are evolving toward multimodal agents capable of proactively executing tasks. Most agent research focuses on GUI or embodied scenarios, which corre…