Fan Zhang

Karl28's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 models 2 days ago

Karl28/RSIPO-SFT-Qwen2.5-7B-Instruct-Search

Text Generation • 8B • Updated 2 days ago • 364

Karl28/RSIPO-SFT-Qwen2.5-7B-Instruct-ALFWorld

Text Generation • 8B • Updated 2 days ago • 319

updated 4 models 3 days ago

Karl28/RSIPO-SFT-Qwen2.5-3B-Instruct-Search

Text Generation • 3B • Updated 3 days ago • 224

Karl28/RSIPO-SFT-Qwen2.5-3B-Instruct-ALFWorld

Text Generation • 3B • Updated 3 days ago • 197

Karl28/RSIPO-SFT-Qwen3-1.7B-Search

Text Generation • 2B • Updated 3 days ago • 73

Karl28/RSIPO-SFT-Qwen3-1.7B-ALFWorld

Text Generation • 2B • Updated 3 days ago • 77

updated a dataset 3 days ago

Karl28/RSIPO-SFT-Data

Viewer • Updated 3 days ago • 24k • 145

published 6 models 3 days ago

Karl28/RSIPO-SFT-Qwen3-1.7B-Search

Text Generation • 2B • Updated 3 days ago • 73

Karl28/RSIPO-SFT-Qwen3-1.7B-ALFWorld

Text Generation • 2B • Updated 3 days ago • 77

Karl28/RSIPO-SFT-Qwen2.5-7B-Instruct-Search

Text Generation • 8B • Updated 2 days ago • 364

Karl28/RSIPO-SFT-Qwen2.5-7B-Instruct-ALFWorld

Text Generation • 8B • Updated 2 days ago • 319

Karl28/RSIPO-SFT-Qwen2.5-3B-Instruct-Search

Text Generation • 3B • Updated 3 days ago • 224

Karl28/RSIPO-SFT-Qwen2.5-3B-Instruct-ALFWorld

Text Generation • 3B • Updated 3 days ago • 197

published a dataset 3 days ago

Karl28/RSIPO-SFT-Data

Viewer • Updated 3 days ago • 24k • 145

authored 6 papers 14 days ago

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

Paper • 2610.15772 • Published 17 days ago • 9

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

Paper • 2609.38541 • Published 29 days ago • 33

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

Paper • 2609.23784 • Published Sep 20 • 16

VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding

Paper • 2608.14718 • Published Aug 12 • 11

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published Jul 16 • 106

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

Paper • 2607.07820 • Published Jul 8 • 95