Search

Tag: #visual-reasoning12 results

7B AdaReasoner Outperforms GPT-5 Visually

AdaReasoner, a 7B model accepted to ICLR 2026, beats GPT-5 on visual puzzles via dynamic tool orchestration in Agentic Vision. Learns what, when, and how to use visual tools iteratively, mimicking human investigation.

机器之心Media•Feb 15#research#adareasoner#7b

TwiFF Enables Dynamic Visual CoT

TwiFF-2.7M dataset and model advance VCoT for videos via future frame generation. TwiFF-Bench evaluates reasoning trajectories. Outperforms baselines on dynamic VQA.

ArXiv AIResearch•Feb 12#research#twiff#v1