Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
Paper
•
2412.19326
•
Published
•
18
•
2
yinanhe
ynhe
AI & ML interests
None yet
Recent Activity
new activity
about 1 hour ago
OpenGVLab/VideoMAEv2-Base:Mapping with labels
new activity
about 2 hours ago
OpenGVLab/InternVideo2-Chat-8B:输出结果为空
updated
a dataset
3 days ago
Vchitect/VBench_human_annotation
Organizations
ynhe's activity
Mapping with labels
1
#1 opened 2 days ago
by
nogayevnuras
Apply for the demo of InternVideo2.5(already open-resourced)
#1 opened 7 days ago
by
ynhe
Demo example in the paper
7
#6 opened 24 days ago
by
willsky
Grammar fix on tab title
#7 opened about 2 months ago
by
Rsln
Add paper link and library name
#1 opened 2 months ago
by
nielsr
commented
a
paper
2 months ago
video/nturgbd/ not found
2
#5 opened 3 months ago
by
hua-zi
How to submit to the VBenchI2V LeaderBoard?
3
#6 opened 4 months ago
by
zhuhz22
Sorry for miss upload.Please delete a result in the leaderboard
1
#6 opened 4 months ago
by
chenamin
How to get source dataset?
3
#3 opened 8 months ago
by
dceaser
the video id in annotation json files not consistent with source video data
1
#4 opened 4 months ago
by
Jingtong-Zhao
where is the video dataset?
1
#5 opened 4 months ago
by
Moses25
Please remove duplicated row of Allegro
1
#5 opened 5 months ago
by
hyang0511
What was the training setting of qformer, LLM?
1
#9 opened 5 months ago
by
vigneshwar472
why is the weights file for InternVideo2-stage2_1b-224p-f4.pt labeled suspicious?
2
#1 opened 5 months ago
by
ellemac
Fix pipeline tag
#8 opened 5 months ago
by
merve
Apply for community grant: Academic project(gpu)
3
#1 opened 6 months ago
by
ynhe
Weights not loading correctly to the base model
6
#2 opened 5 months ago
by
maranadha777