Christian Wolf

chriswolfvision.bsky.social

24 June 2026 09:10

#ECCV2026 paper: A scalar per patch from pre-trained ViTs enables fast moving navigation in the real world 966 *REAL* nav episodes (!!) performed by S. Janny with Dino-v3, Dino-v2, DUNE, VC1, AM-RADIO encoders show that patch features can be bottlenecked to 1 value ➡️ affordances emerge. 1/8

Max Planck Institute for Informatics

mpi-inf.mpg.de

14 February 2026 13:09

Science where it’s rarely present: “Heimspiel Wissenschaft” brings researchers back to their rural homes to talk about their work. @oduenkel.bsky.social spoke in Boxberg-Schwabhausen on generative AI. 86 attendees in a village of ~600 people, plus a lively Q&A.🎓 ↪️https://sic.link/heimspiel

Thaddäus Wiedemer

thwiedemer.bsky.social

03 February 2026 19:43

How useful are self-generated 'mental images' (visual aids) in MLLM/UMM reasoning? Turns out: currently not very. Visualizations have small errors that compound in multi-step problems, and models often ignore correct visual aids in their decision making.

jana-z.bsky.social

03 February 2026 19:39

Can AI reason by “imagining” — not just by seeing or reading? We introduce Mentis Oculi, a benchmark for machine mental imagery: multi-step visual puzzles that require maintaining and updating visual states over time. 📄 arxiv.org/abs/2602.02465 🌐 jana-z.github.io/mentis-oculi/ 🧵⬇️

Computer Vision and Machine Learning at MPI Informatics

cvml.mpi-inf.mpg.de

19 October 2025 20:48

ICCV 2025 🌺 Aloha from Hawaii! MPI-INF (D2) is presenting 4 papers this year (one Highlight). Thread 👇