Odysseus-Project

Odysseus-Project's activity

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

shichengshuai98 

updated a collection 3 months ago

Odysseus

Collection

The models from the paper "Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning", trained to play Super Mario Land • 2 items • Updated May 25

shichengshuai98 

updated a model 3 months ago

Odysseus-Project/Odysseus-Zero

Image-Text-to-Text • 9B • Updated May 25 • 5 • 3

shichengshuai98 

published a model 3 months ago

Odysseus-Project/Odysseus-Zero

Image-Text-to-Text • 9B • Updated May 25 • 5 • 3

shichengshuai98 

updated a model 3 months ago

Odysseus-Project/Odysseus

Image-Text-to-Text • 9B • Updated May 25 • 2

shichengshuai98 

published a model 3 months ago

Odysseus-Project/Odysseus

Image-Text-to-Text • 9B • Updated May 25 • 2

shichengshuai98 

authored 4 papers 3 months ago

MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI

Paper • 2605.08678 • Published May 9 • 9

Building Math Agents with Multi-Turn Iterative Preference Learning

Paper • 2409.02392 • Published Sep 4, 2024 • 16

Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources

Paper • 2306.08364 • Published Jun 14, 2023

Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning

Paper • 2605.00347 • Published May 1 • 16