Notas del episodio
🤗 Upvotes: 58 | cs.CL, cs.AI, cs.CV, cs.LG, cs.MM
作者:
Yu Zhou, Cheng-Fu Yang, Rui Sun, Di Wu, Sibo Peng, Mingyang Zhang, Zhen Yang, Ruiyi Zhang, Nanyun Peng, Zhe Gan, Kai-Wei Chang
标题:
OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
Arxiv:
http://arxiv.org/abs/2610.26860v1
摘要:
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled study on 22 benchmarks shows that simply increasing the inference budget of the base model…
Web: share.transistor.fm

