New paper: ThinkMorph introduces a unified multimodal model that interleaves text and image reasoning steps setting a new benchmark for vision-centric tasks. It’s not just another CoT model. It’s a rethink of how language and vision should collaborate.
November 5, 2025 at 9:48 AM
New paper: ThinkMorph introduces a unified multimodal model that interleaves text and image reasoning steps setting a new benchmark for vision-centric tasks. It’s not just another CoT model. It’s a rethink of how language and vision should collaborate.
The AI hardware industry is betting big on low-precision floating-point formats like FP8. But what if integer formats are actually better for both accuracy and efficiency?
A new paper challenges the FP-first narrative🧵
A new paper challenges the FP-first narrative🧵
November 4, 2025 at 7:40 AM
The AI hardware industry is betting big on low-precision floating-point formats like FP8. But what if integer formats are actually better for both accuracy and efficiency?
A new paper challenges the FP-first narrative🧵
A new paper challenges the FP-first narrative🧵