ODYSSIM
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Benchmark Test-Time Scaling of General LLM Agents
On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
models 9
cmu-lti/osim-4b-mid
Text Generation • 4B • Updated • 59
cmu-lti/osim-4b-inst
Image-Text-to-Text • 5B • Updated • 19
cmu-lti/osim-4b
Text Generation • 4B • Updated • 86
cmu-lti/osim-8b
Text Generation • 8B • Updated • 1.33k • 9
cmu-lti/osim-8b-mid
Text Generation • 8B • Updated • 187 • 2
cmu-lti/sotopia-pi-mistral-7b-BC_SR
Updated • 7
cmu-lti/sotopia-pi-mistral-7b-SR
Updated • 6
cmu-lti/sotopia-pi-mistral-7b-BC
Updated • 3
cmu-lti/sotopia-pi
Updated • 9
datasets 15
cmu-lti/osim-post-training
Viewer • Updated • 33.5k • 166 • 1
cmu-lti/osim-mid-training
Viewer • Updated • 21.2M • 299 • 4
cmu-lti/tau-usi
Updated • 43 • 6
cmu-lti/machine-translation-for-vision
Viewer • Updated • 696 • 74 • 3
cmu-lti/stateful
Viewer • Updated • 500 • 99
cmu-lti/caire-specific
Viewer • Updated • 68 • 28
cmu-lti/interactive-swe
Viewer • Updated • 500 • 123 • 1
cmu-lti/caire-universal
Viewer • Updated • 400 • 33
cmu-lti/caire-index-ckpts
Updated • 6
cmu-lti/AI-LieDar
Updated • 32