{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/0f624c26551b4273b33371358c3164d3\" frameborder=\"0\" width=\"1668\" height=\"1251\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1251,"width":1668,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1251,"thumbnail_width":1668,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/0f624c26551b4273b33371358c3164d3-6719ec66493fe0f9.gif","duration":316.24,"title":"Bridging Large Language Models and Molecular Graphs for Enhanced Understanding 🌌","description":"In this video, I discuss my recent work accepted by ICLR 2026, which focuses on bridging large-language models with molecular graphs. We address the challenges posed by different molecular modalities and propose two key innovations: entropy-guided patching to preserve molecular structure and a DynamicQueryFormer that enhances the Q-former framework. Our model demonstrates superior performance across various benchmarks, including multiple-choice questions and property generation tasks. I encourage viewers to review our findings and consider the implications for future research in this area."}