7 papers
ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation
Jiahao Zhao, Xiaomin Yu, Zhongxiang Sun +5
Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require complex semantic understanding, multi-step reasoning, an…
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
Xiaomin Yu, Yi Xin, Yuhui Zhang +12
Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of d…
LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling
Wenkai Chen, Tianshu Li, Wenyong Huang +3
Mixture-of-Experts (MoE) and looped architectures scale models along two orthogonal axes, namely parameter capacity and effective depth. However, mainstream looped architectures re…
Text-Only Data Synthesis for Vision Language Model Training
Xiaomin Yu, Wenjie Zhang, Ziyue Qiao +2
Training vision-language models (VLMs) typically requires large-scale, high-quality image-text pairs, but collecting or synthesizing such data is costly. In contrast, text data is…
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
Chengwen Liu, Xiaomin Yu, Zhuoyue Chang +15
In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore ne…
ICRL: Learning to Internalize Self-Critique with Reinforcement Learning
Jianbo Lin, Xiaomin Yu, Yi Xin +7
Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed, the model may fail again on…