Fangyuan Yu PRO
Ksgk-fy
AI & ML interests
AGI
Recent Activity
upvoted
a
paper
4 days ago
GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
updated
a model
9 days ago
Ksgk-fy/sorl_pt
published
a model
9 days ago
Ksgk-fy/sorl_pt
Organizations
-
Accelerating Exploration with Unlabeled Prior Data
Paper • 2311.05067 • Published • 2 -
Efficient Online Reinforcement Learning with Offline Data
Paper • 2302.02948 • Published • 2 -
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
Paper • 2407.04620 • Published • 34 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 263
-
Accelerating Exploration with Unlabeled Prior Data
Paper • 2311.05067 • Published • 2 -
Efficient Online Reinforcement Learning with Offline Data
Paper • 2302.02948 • Published • 2 -
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
Paper • 2407.04620 • Published • 34 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 263
models
235
Ksgk-fy/sorl_pt
Updated
Ksgk-fy/mbe-gpt2-medium-fineweb10B
0.4B
•
Updated
•
1
Ksgk-fy/iblm-gpt2-xl-fineweb10B
2B
•
Updated
Ksgk-fy/gpt2-xl-fineweb10B
2B
•
Updated
•
1
Ksgk-fy/iblm-gpt2-medium-fineweb10B
0.4B
•
Updated
•
1
Ksgk-fy/gpt2-medium-fineweb10B
0.4B
•
Updated
•
6
Ksgk-fy/iblm2-gpt2-medium-fineweb10B
0.4B
•
Updated
•
1
Ksgk-fy/iblm-gpt2-large-fineweb10B
0.8B
•
Updated
•
1
Ksgk-fy/iblm-gpt2-small-fineweb10B
0.2B
•
Updated
•
4
Ksgk-fy/gpt2-large-fineweb10B
0.8B
•
Updated
•
2
datasets
18
Ksgk-fy/inception-kanji-dataset-512
Viewer
•
Updated
•
31.3k
•
17
Ksgk-fy/inception-kanji-dataset
Viewer
•
Updated
•
74k
•
14
Ksgk-fy/concept-augmented-kanji-dataset
Viewer
•
Updated
•
175k
•
19
Ksgk-fy/concept-kanji-dataset
Viewer
•
Updated
•
21.2k
•
11
Ksgk-fy/augmented-kanji-dataset
Viewer
•
Updated
•
175k
•
24
Ksgk-fy/expanded-kanji-dataset
Viewer
•
Updated
•
21.2k
•
13
Ksgk-fy/kanji-dataset
Viewer
•
Updated
•
3.43k
•
24
Ksgk-fy/gsm8k
Viewer
•
Updated
•
8.79k
•
18
Ksgk-fy/genius_upload
Viewer
•
Updated
•
9.04k
•
7
•
2
Ksgk-fy/glaive-function-calling-mlx
Updated
•
4