Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
Paper • 2603.28489 • Published • 25
Isaache
Isaachhe
AI & ML interests
None yet
Recent Activity
authored a paper about 6 hours ago
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms upvoted a paper about 12 hours ago
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms new activity almost 2 years ago
microsoft/Phi-3-vision-128k-instruct:Unable to Reproduce Results of Any Model on the Evaluation LeaderboardOrganizations
None yet
authored a
paper about 6 hours ago
upvoted a paper about 12 hours ago
Unable to Reproduce Results of Any Model on the Evaluation Leaderboard
👀 1
4
#9 opened almost 2 years ago
by 
tcy6
Support for Bunny
👍 1
2
#5 opened about 2 years ago
by Isaachhe
updated a
model about 2 years ago
Thanks for your attention!
We have tried two vision encoders and three LLMs. The best performances are achieved by integrating SigLIP-SO and Phi-2. We released all weights of combinations. Please refer to our GitHub for more information.
[bot] Conversion to Parquet
#1 opened over 2 years ago
by 
parquet-converter