arxiv:2610.15772
Fan Zhang
Karl28
AI & ML interests
Multimodal Agent
Recent Activity
authored a paper about 8 hours ago
RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution authored a paper about 8 hours ago
ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing authored a paper about 8 hours ago
PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin PackingOrganizations
models 10
Karl28/RSIPO-Qwen2.5-7B-Instruct-Search
Text Generation • 8B • Updated • 37 • 1
Karl28/RSIPO-Qwen2.5-7B-Instruct-ALFWorld
Text Generation • 8B • Updated • 14
Karl28/RSIPO-Qwen2.5-3B-Instruct-Search
Text Generation • 3B • Updated • 17
Karl28/RSIPO-Qwen2.5-3B-Instruct-ALFWorld
Text Generation • 3B • Updated • 22
Karl28/RSIPO-Qwen3-1.7B-Search
Text Generation • 2B • Updated • 20
Karl28/RSIPO-Qwen3-1.7B-ALFWorld
Text Generation • 2B • Updated • 21
Karl28/UniFER-SFT-7B
8B • Updated • 8
Karl28/Orchestra-o1-8B
8B • Updated • 9 • 4
Karl28/Emotion-Adapters
Text Generation • Updated • 10
Karl28/UniFER-7B
8B • Updated • 16