visual-recognition

Tag

Cards List
#visual-recognition

@jerryjliu0: We benchmarked Gemini 3.6 Flash and Gemini 3.5 Flash Lite on document understanding. We compared against their prior ve…

X AI KOLs Following · 2d ago Cached

This tweet benchmarks Gemini 3.6 Flash and Gemini 3.5 Flash Lite on document understanding, finding that while the Flash series initially excelled at visual understanding, recent versions have plateaued or regressed due to posttraining for coding and reasoning.

0 favorites 0 likes
#visual-recognition

@FinanceYF5: Someone built a customer acquisition system for renovation contractors using Fable 5. It scrapes houses sold locally in the past 12 months, uses visual recognition to skip yards with existing shade, calculates how long the yard has been exposed to sun using satellite data, renders a pergola into the homeowner's own yard photo, prints it onto a postcard and mails it. Each lead is quoted between $6,500 and $18,000. This acquisition...

X AI KOLs Following · 2026-07-06 Cached

Someone built a customer acquisition system using Fable 5 that generates postcards with pergola effects for renovation contractors via visual recognition, satellite data, and rendering technology. Each lead is quoted between $6,500 and $18,000.

0 favorites 0 likes
#visual-recognition

MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching

Hugging Face Daily Papers · 2026-05-08 Cached

MC-RFM proposes a novel Riemannian flow-matching framework for few-shot adaptation that models feature displacement on a mixed-curvature manifold combining hyperbolic and Euclidean spaces, outperforming existing methods across multiple visual recognition benchmarks.

0 favorites 0 likes
← Back to home

Submit Feedback