arxiv:2601.01739
yoon
sangyon
AI & ML interests
None yet
Recent Activity
liked
a model
2 days ago
trillionlabs/Trida-7B
authored
a paper
28 days ago
SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early
Alignment
authored
a paper
28 days ago
R-TOFU: Unlearning in Large Reasoning Models
Organizations
None yet
datasets
9
sangyon/R-TOFU
Viewer
•
Updated
•
10.6k
•
81
sangyon/R-TOFU1
Viewer
•
Updated
•
10.6k
•
45
sangyon/retain10
Viewer
•
Updated
•
400
•
1
sangyon/retain50
Viewer
•
Updated
•
2k
•
1
sangyon/retain90
Viewer
•
Updated
•
3.6k
•
19
sangyon/forget10
Viewer
•
Updated
•
3.6k
•
1
sangyon/forget05
Viewer
•
Updated
•
2k
•
5
sangyon/forget01
Viewer
•
Updated
•
400
•
4
sangyon/Reasoned_IDK
Viewer
•
Updated
•
400
•
6