{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/fac4e76448584b5c87f1c0b86b6d58c7\" frameborder=\"0\" width=\"1680\" height=\"1260\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1260,"width":1680,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1260,"thumbnail_width":1680,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/fac4e76448584b5c87f1c0b86b6d58c7-4e68915532ce234a.gif","duration":129.216,"title":"DensityGen for Smarter Chip Metal Precursors","description":"This Loom presents DensityGen, a system to screen and rank chemical precursor candidates for advanced chip manufacturing. It explains that as copper wire features shrink, heat and cooling challenges increase, driving the need for better metal-depositing precursors to meet the latest chip designs with less power. The speaker highlights molybdenum precursor selection as a major defense-related challenge, noting China’s capacity for molybdenum. DensityGen uses a backend database powered by 500 million atoms by Meta and queries an UMA model that transitions between molecular and crystal databases, ranking candidates on seven axes for chemists."}