Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities
AI & ML interests
AI, ML, CV, NLP, Robotics
Recent Activity
View all activity
models 11
omron-sinicx/DGPO-qwen2.5-0.5b
Text Generation • 0.6B • Updated • 73
omron-sinicx/SearchR1-ppo-qwen2.5-3b-instruct
3B • Updated • 63 • 1
omron-sinicx/Qwen2.5-0.5B-Instruct-sft
0.5B • Updated • 27
omron-sinicx/Qwen2.5-0.5B-Instruct-kd
0.5B • Updated • 155
omron-sinicx/SearchR1-ppo-qwen2.5-7b-instruct
8B • Updated • 17 • 1
omron-sinicx/SearchR1-ppo-llama3.1-8b-instruct
8B • Updated • 24 • 1
omron-sinicx/Llama-3.2-1B-Instruct-kd
1B • Updated • 15
omron-sinicx/sbsfigures-chartqa-pix2struct
Updated • 1
omron-sinicx/sbsfigures-chartqa-donut
Updated • 1
omron-sinicx/sbsfigures-pretrain-donut
Updated • 1
datasets 12
omron-sinicx/MaterialFigBench
Viewer • Updated • 115 • 378
omron-sinicx/scipostlayouttree
Updated • 38
omron-sinicx/MaterialBENCH
Updated • 34
omron-sinicx/AlignBench
Viewer • Updated • 102k • 4.01k • 2
omron-sinicx/sbsfigures
Viewer • Updated • 4.17M • 312 • 4
omron-sinicx/scipostgen
Preview • Updated • 9
omron-sinicx/PMC-Vid
Preview • Updated • 19
omron-sinicx/synthetic_language
Preview • Updated • 6
omron-sinicx/wiki2023_plus
Viewer • Updated • 7.4k • 73 • 1
omron-sinicx/scipostlayout_v2
Preview • Updated • 26 • 7