Learning Native Reflection in Unified Models: SFT and RL checkpoints of BAGEL-7B-MoT and the reflection-SFT data.
walt stephen
YijiaFan
AI & ML interests
None yet
Recent Activity
upvoted a paper about 9 hours ago
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards updated a model 4 days ago
YijiaFan/pi05-shou-zhua-bing-8skills-sf-20261009-60k updated a dataset 4 days ago
YijiaFan/model-train-runtimeOrganizations
models 8
YijiaFan/pi05-shou-zhua-bing-8skills-sf-20261009-60k
Updated
YijiaFan/spline-egg-sponge-cake-v3-7skills-fullvideo-20261005-90k
Updated
YijiaFan/pi05-egg-sponge-cake-v3-7skills-fullvideo-20261005-90k
Updated
YijiaFan/spline-egg-sponge-cake-v3-6skills-fullvideo-20261004-30k
Updated
YijiaFan/pi05-egg-sponge-cake-v3-6skills-fullvideo-20261004-60k
Updated
YijiaFan/pi05-egg-sponge-cake-v3-5skills-20261001-90k
Updated
YijiaFan/UMM-Reflection-BAGEL-RL
Any-to-Any • Updated • 317 • 5
YijiaFan/UMM-Reflection-BAGEL-SFT
Any-to-Any • Updated • 30 • 1