2 papers
cs.LG2026
ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-Seeking Agents
Cong Pang, Xuyu Feng, Yujie Yi +7
Despite the strong performance achieved by reinforcement learning-trained information-seeking agents, learning in open-ended web environments remains severely constrained by low si…
cs.CV2025
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Jinguo Zhu, Weiyun Wang, Zhe Chen +48
We introduce InternVL3, a significant advancement in the InternVL series featuring a native multimodal pre-training paradigm. Rather than adapting a text-only large language model…