Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
Paper
•
2503.15558
•
Published
•
51
Enpei Zhao
enpeizhao
AI & ML interests
None yet
Recent Activity
updated
a Space
about 19 hours ago
enpeizhao/VLM_ODD_Online_Demo
published
a Space
5 days ago
enpeizhao/VLM_ODD_Online_Demo
replied to
sergiopaniego's
post
5 days ago
Yet Another New Multimodal Fine-Tuning Recipe 🥧
🧑🍳 In this @HuggingFace Face Cookbook notebook, we demonstrate how to align a multimodal model (VLM) using Mixed Preference Optimization (MPO) using trl.
💡 This recipe is powered by the new MPO support in trl, enabled through a recent upgrade to the DPO trainer!
We align the multimodal model using multiple optimization objectives (losses), guided by a preference dataset (chosen vs. rejected multimodal pairs).
Check it out! ➡️ https://huggingface.co/learn/cookbook/fine_tuning_vlm_mpo
Organizations
None yet
upvoted
a
paper
4 months ago