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
microsoft/VibeVoice-AcousticTokenizer
Feature Extraction • 0.7B • Updated • 1.92k • • 22
microsoft/InfoAgent
Updated • 16
microsoft/paza-Phi-4-multimodal-instruct
Automatic Speech Recognition • 6B • Updated • 3.39k • 10
microsoft/paza-whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 2.6k • 16
microsoft/Dayhoff-3b-GR-HM-1000
Text Generation • 3B • Updated • 350 • 5
microsoft/Dayhoff-170M-GR-1000
Text Generation • 0.2B • Updated • 358 • 7
microsoft/Dayhoff-170M-UR90-1000
Text Generation • 0.2B • Updated • 368 • 5
microsoft/X-Reasoner-7B
Image-Text-to-Text • 8B • Updated • 1.48k • 16
microsoft/SNRAware
Updated • 3
microsoft/VibeVoice-ASR
Automatic Speech Recognition • 9B • Updated • 704k • 1.33k
microsoft/Dayhoff-3b-GR-HM-41000
Text Generation • 3B • Updated • 362 • 5
microsoft/Dayhoff-3b-GR-HM-31000
Text Generation • 3B • Updated • 350 • 4
microsoft/Dayhoff-3b-GR-HM-21000
Text Generation • 3B • Updated • 370 • 5
microsoft/Dayhoff-3b-GR-HM-11000
Text Generation • 3B • Updated • 357 • 7
microsoft/Dayhoff-170M-GR-61000
Text Generation • 0.2B • Updated • 381 • 6
microsoft/Dayhoff-170M-GR-46000
Text Generation • 0.2B • Updated • 365 • 6
microsoft/Dayhoff-170M-GR-31000
Text Generation • 0.2B • Updated • 391 • 4
microsoft/Dayhoff-170M-GR-16000
Text Generation • 0.2B • Updated • 359 • 3
microsoft/Dayhoff-170M-UR90-61000
Text Generation • 0.2B • Updated • 364 • 5
microsoft/Dayhoff-170M-UR90-46000
Text Generation • 0.2B • Updated • 337 • 2
microsoft/Dayhoff-170M-UR90-31000
Text Generation • 0.2B • Updated • 623 • 7
microsoft/Dayhoff-170M-UR90-16000
Text Generation • 0.2B • Updated • 358 • 4
microsoft/Dayhoff-3b-GR-HM-c
Text Generation • 3B • Updated • 1.23k • 12
microsoft/Dayhoff-3b-GR-HM
Text Generation • 3B • Updated • 369 • 7
microsoft/Dayhoff-3b-UR90
Text Generation • 3B • Updated • 583 • 6
microsoft/Dayhoff-170m-UR50-BRn
Text Generation • 0.2B • Updated • 381 • 6
microsoft/Dayhoff-170m-UR50-BRq
Text Generation • 0.2B • Updated • 344 • 4
microsoft/Dayhoff-170m-UR50-BRu
Text Generation • 0.2B • Updated • 674 • 9
microsoft/Dayhoff-170m-GR
Text Generation • 0.2B • Updated • 370 • 7
microsoft/Dayhoff-170m-UR90
Text Generation • 0.2B • Updated • 368 • 6