@pointscoder : Can Vision-Language Models (VLMs) truly understand the physical world? 🌍🔬 Introducing PhysBench – the first benchmark to evaluate VLMs’ understanding of physics! PhysBench is accepted to #ICLR25025 as an Oral presentation (only 1.8% out of 11k submissions)! 🌐 Project: • TwiCopy

Jiageng Mao

@pointscoder

+ Follow

PhD Student @ USC CS

ID: 1417811875480309761

linkhttp://PointsCoder.github.io calendar_today21-07-2021 11:50:00

50 Tweet

406 Followers

399 Following

Jiageng Mao

@pointscoder

9 months ago

Can Vision-Language Models (VLMs) truly understand the physical world? 🌍🔬 Introducing PhysBench – the first benchmark to evaluate VLMs’ understanding of physics! PhysBench is accepted to #ICLR2025 as an Oral presentation (only 1.8% out of 11k submissions)! 🌐 Project:

thumb_up_off_alt413

chat_bubble_outline5

repeat73

shareShare