Author of "InternVL 3.5: Open Multimodal Reasoning Model" on arXiv
How media typically covers Hengjun Pu
Hengjun Pu as author
InternVL 3.5 introduces Cascade Reinforcement Learning and Visual Resolution Router to achieve 16% reasoning performance gains and 4.05x inference speedup while approaching performance parity with commercial models like GPT-4.
“Author of "InternVL 3.5: Open Multimodal Reasoning Model" on arXiv”