Using latent chain-of-thoughts instead of explicit reasoning steps.
yubin
VLyb
AI & ML interests
LLM, AI for Education
Recent Activity
upvoted
a
paper
about 2 hours ago
Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds
upvoted
a
paper
10 days ago
MR-Align: Meta-Reasoning Informed Factuality Alignment for Large
Reasoning Models
upvoted
a
paper
14 days ago
Scaling Latent Reasoning via Looped Language Models
Organizations
datasets
12
VLyb/OpenThoughts-ReasonFluxPRM-distill
Viewer
•
Updated
•
134k
•
15
VLyb/s1K-mix
Viewer
•
Updated
•
1.98k
•
29
•
1
VLyb/UMLS
Viewer
•
Updated
•
6.53k
•
34
•
4
VLyb/Kinship
Viewer
•
Updated
•
10.7k
•
21
VLyb/DBpedia500
Viewer
•
Updated
•
4.27M
•
18
•
2
VLyb/DBpedia50
Viewer
•
Updated
•
43.8k
•
14
VLyb/Nations
Viewer
•
Updated
•
1.99k
•
24
VLyb/YAGO3-10
Viewer
•
Updated
•
1.09M
•
66
VLyb/WN18RR
Viewer
•
Updated
•
93k
•
206
•
1
VLyb/FB15k-237
Viewer
•
Updated
•
310k
•
102