Aosong Feng
afeng
AI & ML interests
古希腊掌管 gpu 的神
Recent Activity
upvoted a paper about 1 month ago
Improving Test-Time Scaling with Adaptive Looped TransformersOrganizations
models 22
afeng/qwen3-8b-finqa-rl-checkpoints
Updated • 1
afeng/step566-VO-Qwen3-14B-0p0001beta-factor0p005-noise-p0p0-v1
15B • Updated • 8
afeng/step566-VO-Qwen3-14B-0p0005beta-factor0p0005-noise-p0p0-v1
15B • Updated • 5
afeng/step566-VO-Qwen3-14B-0p0005beta-factor0p001-noise-p0p0-v1
15B • Updated • 4
afeng/step566-VO-Qwen3-8B-0p0005beta-factor0p001-noise-p0p0-v1
8B • Updated • 3
afeng/step566-VO-Qwen3-8B-0p0005beta-factor0p0025-noise-p0p0-v1
8B • Updated • 5
afeng/step566-VO-Qwen3-14B-0p0001beta-factor0p0005-noise-p0p0-v2
15B • Updated • 12
afeng/step566-VO-Qwen3-14B-0p0001beta-factor0p001-noise-p0p0-v2
15B • Updated • 3
afeng/step566-VO-Qwen3-14B-0p0005beta-factor0p0025-noise-p0p0-v2
15B • Updated • 3
afeng/step400-VO-Qwen3-14B-0p0005beta-factor0p025-noise-p0p0-v1
15B • Updated • 7