Fan Zhang

Karl28

·

https://zfkarl.github.io

zfkarl

AI & ML interests

Multimodal Agent

Recent Activity

authored a paper 1 day ago

RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution

authored a paper 1 day ago

ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing

authored a paper 1 day ago

PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing

View all activity

Organizations

Karl28 's papers 18

arxiv:2610.15772

arxiv:2609.38541

arxiv:2609.23784

arxiv:2609.04131

arxiv:2608.14718

arxiv:2607.14777

arxiv:2607.07820

arxiv:2606.26790

arxiv:2606.13707

arxiv:2606.09826

arxiv:2606.07689

arxiv:2605.22177

arxiv:2605.06234

arxiv:2604.19417

arxiv:2508.09210

arxiv:2508.01318

arxiv:2504.15585

arxiv:2503.21460