GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation
Paper
•
2512.17495
•
Published
•
19
POLARIS
community
AI & ML interests
POLARIS is an open-source project focusing on post-training advanced reasoning models. It is jointly maintained by the University of Hong Kong and ByteDance Seed.
Recent Activity
View all activity
tobiaslee
authored
a
paper
8 days ago
tobiaslee
submitted
a
paper
to Daily Papers
8 days ago
Chancy
updated
a
model
6 months ago
Chancy
published
a
model
6 months ago
Chancy
updated
2
models
6 months ago
Chancy
published
a
model
6 months ago
Thank you!
❤️
5
7
#1 opened 6 months ago
by
owao
Chancy
updated
a
model
6 months ago
Chancy
published
2
models
6 months ago
Chancy
updated
a
dataset
6 months ago
Chancy
published
a
dataset
7 months ago
tobiaslee
authored
a
paper
7 months ago
tobiaslee
authored
6
papers
8 months ago
GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models
Paper
•
2412.12735
•
Published
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey
Paper
•
2412.18619
•
Published
•
58
ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom
Paper
•
2410.14138
•
Published
LONGCODEU: Benchmarking Long-Context Language Models on Long Code Understanding
Paper
•
2503.04359
•
Published
•
6
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
Paper
•
2504.17343
•
Published
•
13
MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
Paper
•
2505.07608
•
Published
•
82