3 papers
cs.CL2026
Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs
Mengdan Zhu, Senhao Cheng, Liang Zhao
Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the cost of tool calls or rely on…
cs.CV2025
Cross-modal RAG: Sub-dimensional Text-to-Image Retrieval-Augmented Generation
Mengdan Zhu, Senhao Cheng, Guangji Bai +2
Text-to-image generation increasingly demands access to domain-specific, fine-grained, and rapidly evolving knowledge that pretrained models cannot fully capture, necessitating the…
cs.CL2024
ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain
Haochen Zhao, Xiangru Tang, Ziran Yang +8
The advancement and extensive application of large language models (LLMs) have been remarkable, including their use in scientific research assistance. However, these models often g…