Yağız Ergüzel

Boğaziçi eee
building @microagi

[Yağız Ergüzel @ErguzelYag]

We trained a model for robotic sub-action annotation that outperforms state-of-the-art models at a fraction of the cost! Thanks to the team for the help!

[Animesh Garg @animesh_garg]

Two new egocentric benchmarks from @microagi evaluate VLM readiness for robotics:
MicroPlanBench and MicroAnnotationBench.

tl;dr: Semantic reasoning ≠ perceptual timing
A lot of work to do.

MicroPlanBench (consequential next-action planning)
When predicting the single valid next atomic action from 8s of egocentric video, SOTA models still fail ~1/3 of the time (GPT-6 Astra: 65.6%, GPT-6.1 Sol: 65.5% at 1/5th cost).
- GPT-6 Astra error breakdown: 60% wrong manipulation, 23% wrong hand assignment, 17% wrong object/destination.
- Across all flags, 42% of failures involve tracking the wrong hand.
https://t.co/Yd6cvJSiuh

MicroAnnotationBench (continuous temporal grounding)
Knowing what happens ≠ knowing when
Continuous 60s+ dense manipulation video remains unsolved for generalist VLMs:
- GPT-6 Astra/Sol over-segment (~22 segments/clip vs. 13.8 human mean), collapsing precision (~39%) and strict Boundary F1 (<20%).
- Scaling Test-time compute fails to fix perceptual boundaries: scaling Gemini 4 Argon to high reasoning effort dropped its headline score by 4.9 points while costing 4.7x more
https://t.co/LbEfZblJbJ

Currently, Small specialists match/beat frontier APIs at scale.
@microagi's self-hosted nanoannot-1 outperforms the frontier models (Gemini 4 Argon) across the board:
- 54.8 vs 49.6 overall;
- 32.9 vs 27.3 on strict ± 0.667s Boundary F1
- ~1/10th the cost (~$0.30 vs $3.14/video hr & >300x cheaper than GPT 6 Astra)

Solid work by @ErguzelYag, Ömer Adanir & Team.

[Yağız Ergüzel @ErguzelYag]

@animesh_garg @microagi This is just the beginning 🚀

[Yağız Ergüzel @ErguzelYag]

@bercankilic LFG 🚀