AI Briefing#visual-reasoning
The latest AI and developer news about #visual-reasoning, with the original source and a short summary.
The latest AI and developer news about #visual-reasoning, with the original source and a short summary.
The model supports configurable reasoning, structured outputs, and tool calling, with a fast mode option for latency-sensitive work.
The model accepts images and video to track objects and interpret spatial relationships, accessible via the model name elorian/glimpse.
Human participants achieve 93.1% accuracy on the new HSS benchmark, while the top-performing model, GPT-6-astra, reaches only 53.6%.
Researchers from Google DeepMind and Apple have founded Trajectory, an AI startup focused on strengthening visual reasoning capabilities.
MAI-Image-2.5 has been released, ranking 3rd on the Arena text-to-image leaderboard.
Ovis2.6-80B-A3B has been released as an MoE-based multimodal model.
OpenAI unveiled o3 and o4-mini, which perform visual reasoning by directly cropping, zooming, and rotating images.
The visual reasoning model **QVQ-Max**, which analyzes visual information and reasons to present solutions, has been released.