baichuan-inc/Baichuan-M1-14B-Instruct
Updated
•
137k
•
41
Tung-Lin Wu
tunglinwu
AI & ML interests
None yet
Recent Activity
liked
a model
about 2 hours ago
baichuan-inc/Baichuan-M1-14B-Instruct
upvoted
a
paper
7 days ago
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via
Reinforcement Learning
Organizations
None yet
tunglinwu's activity
liked
a
model
about 2 hours ago
upvoted
a
paper
1 day ago
upvoted
a
paper
7 days ago
reacted to
tianchez's
post with 🔥
7 days ago
Post
3994
Introducing VLM-R1!
GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks?
The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task).
https://github.com/om-ai-lab/VLM-R1
GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks?
The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task).
https://github.com/om-ai-lab/VLM-R1
- 2 replies
upvoted
an
article
8 days ago
Article
What is test-time compute and how to scale it?
By
and 1 other
•
•
42
upvoted
an
article
19 days ago
Article
Mixture of Experts Explained
•
410
upvoted
an
article
21 days ago
Article
Open-source DeepResearch – Freeing our search agents
•
1.1k
Missing image files
4
#3 opened about 2 months ago
by
Chunyuan24
How to pre-process the data to finetune the model?
1
#8 opened 2 months ago
by
XiaomanWu
upvoted
a
collection
3 months ago
liked
a
model
3 months ago
liked
a
model
4 months ago
upvoted
a
paper
4 months ago
AquilaMed-RL
2
#2 opened 4 months ago
by
tunglinwu
upvoted
a
collection
4 months ago
upvoted
a
paper
5 months ago
liked
a
dataset
5 months ago
upvoted
a
collection
5 months ago
liked
a
model
6 months ago
liked
a
Space
6 months ago