Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
• 24
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost
Articles
spaces 34
pinned
Running
Agents
30
PazaBench
🥇
ASR Leaderboard for low resource languages
pinned
Running
Agents
4
BizGenEval Leaderboard
🥇
Official BizGenEval leaderboard on Hugging Face.
pinned
Running
Agents
17
MageBench Leaderboard
🥇
This is a leaderboard for magebench
Running
6
VibeVoice ASR Streaming
🌍
Official Playground of Microsoft VibeVoice-ASR-Streaming
Runtime error
MCP
Featured
126
Mage-Flow
🎨
Efficient native-resolution image generation and editing
Running on CPU Upgrade
MCP
Featured
39
VibeVoice ASR BitNet
🎙
Multilingual CPU-only ASR with a 1.58-bit BitNet decoder
models 554
microsoft/Graphormer
Updated • 7
microsoft/Mage-VL-Cowork
Image-Text-to-Text • 5B • Updated • 2.56k • 185
microsoft/rho-yam-box
5B • Updated • 8
microsoft/rho-ur-ai-trainer
5B • Updated • 4
microsoft/Sentiment-Analysis-7B
Text Generation • 7B • Updated • 2.39k • 33
microsoft/scFM-dataselection
Updated • 3
microsoft/bioemu2
Updated • 24
microsoft/UserRepGen-4B
Text Generation • 5B • Updated • 2.7k • 28
microsoft/AesCode-32B
Image-Text-to-Text • 33B • Updated • 2.01k • 58
microsoft/AesCode-8B
Image-Text-to-Text • 9B • Updated • 2.37k • 80
datasets 119
microsoft/SynthDocQA
Preview • Updated • 1.14k • 6
microsoft/SchGen_dataset
Viewer • Updated • 8.42k • 726 • 10
microsoft/CABRA
Updated • 1.7k • 9
microsoft/sigmacollab
Preview • Updated • 783 • 6
microsoft/rushes
Viewer • Updated • 57.2k • 803 • 4
microsoft/ProgramDistill
Updated • 4.04k • 14
microsoft/roboeval-data-for-rho
Viewer • Updated • 2.5k • 605 • 1
microsoft/libero-data-for-rho
Franka Panda • Updated • 1.72k episodes • 9.34k • 4
microsoft/BusyBox
Viewer • Updated • 11.3k • 1.57k • 4
microsoft/WorkflowPerturb
Viewer • Updated • 44.9k • 162 • 3