VictoryLab

community

AI & ML interests

None defined yet.

Recent Activity

mnuouno updated a model 23 days ago

vlabki/poscat-gv2-dual-policy

lakelee authored a paper 6 months ago

STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding

lakelee authored a paper over 1 year ago

ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding

View all activity

vlabki 's models 73

vlabki/rr-speed-v4

Reinforcement Learning • 575k • Updated Aug 26 • 375

vlabki/daisy-circuit-shadow-v1

1 • Updated Aug 21 • 9

vlabki/rr-tw3-bc-ppo-speed-v3-peak-v2-best

575k • Updated Aug 20 • 19

vlabki/rr-tw3-bc-ppo-speed-v3-peak-last

575k • Updated Aug 19 • 14

vlabki/rr-tw3-bc-ppo-speed-v3

575k • Updated Aug 19 • 13

vlabki/rr-tw3-bc-ppo-speed-v2

575k • Updated Aug 18 • 13

vlabki/rr-tw3-bc-ppo-boost-v1

575k • Updated Aug 16 • 15

vlabki/rr-tw3-bc-ppo-wheelie-v1

575k • Updated Aug 15 • 17

vlabki/rr-tw3-bc-ppo-separated-v2

575k • Updated Aug 14 • 7

vlabki/rr-tw3-bc

575k • Updated Aug 11 • 16

vlabki/gv-v1

8.98M • Updated Aug 10 • 10

vlabki/mg-v4-finisher

8.98M • Updated Aug 9 • 15

vlabki/hftest