الباحثون

Yizhe Zhang

المنشورات 2

نسخة أولية وصول مفتوح

SkillFM: Generating Skills for LLM Agents via Latent Flow Matching

Zuming Zhang, Jie He, Yizhe Zhang وآخرون · 2026

Textual skills provide reusable guidance for large language model agents, but existing approaches often rely on manually curated skill banks or reinforcement learning with indirect and delayed feedback. We introduce SkillFM (Skill Flow Matching), a generative framework that synthesizes task-conditioned textual skills d …

نسخة أولية وصول مفتوح

Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning

Multimodal models increasingly think with different modalities such as images, 3D point clouds, and robot states, not just text. Yet each modality is still encoded into its own representation space, creating a modality-switching gap whenever reasoning moves from one modality to another. In this paper, we introduce Uni- …

المؤلفون المشاركون