Frontier VLMs Struggle at Basic 2-DoF Active Visual Search, NeurIPS Paper Finds
_vztu · x · 2026-10-04
A NeurIPS 2026-accepted paper tests whether frontier VLMs can handle something as simple as turning their "head" to locate an object.
- Most frontier VLMs struggle at this basic 2-DoF active visual search task
- The authors find that "imagination in 360°" plays a key role in active visual search performance
- The paper has been accepted to NeurIPS 2026
More from Embodied
- Dev builds a physical control deck to juggle multiple AI coding agent sessions — Weak_Cherry_4878 · 2026-10-04
- NYU's $5 open-source eFlesh magnetic tactile sensor is 3D-printable — lukas_m_ziegler · 2026-10-04
- SPEAR Simulator Opens Up 14K+ Unreal Engine Functions for Embodied AI Research — rsasaki0109 · 2026-10-04
- vLLM creator's new 'roommate' walks like he's had three drinks and says no to everything — Thom_Wolf · 2026-10-04
- Tesla has 589 robotaxis in Texas, tracking two weeks ahead for 3,000 by end of 2026 — mitchdeg · 2026-10-04
- Meta AI Chief Alexandr Wang Praises Rokid Glasses Running Local LLM Anime Companion — alexandr_wang · 2026-10-04