Authors

Yixin Li

Publications 2

Preprint Open access

ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills

Hongxing Li, Dingming Li, Yixin Li et al. · 2026

Skill-augmented agents improve sample efficiency by distilling successful trajectories into reusable strategies. Yet most existing approaches remain text-centric, linearizing spatial layouts and action-state correspondences into language that loses critical geometric structure. Recent efforts have begun incorporating v …

Preprint Open access

Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models

Hongxing Li, Yixin Li, Dingming Li et al. · 2026

Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Existing remedies either inject 3D into the model at inference, paying architecture and latency costs, or train with outcome rewards that supervise only the final answer. Spat …

Co-authors