RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models
Paper • 2607.26991 • Published • 8
William
wilt8
AI & ML interests
NLP, Machine Learning
Recent Activity
authored a paper 4 days ago
RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models updated a dataset about 1 year ago
wilt8/G1_welding_exampleOrganizations
None yet
authored a
paper 4 days ago
upvoted a paper 4 days ago
updated a
dataset about 1 year ago
published a
dataset about 1 year ago
updated 15
models almost 2 years ago
wilt8/codeparrot-ds
Text Generation • 0.1B • Updated • 5
wilt8/rl_course_vizdoom_health_gathering_supreme
Reinforcement Learning • Updated
wilt8/ppo-CleanRL-LunarLander-v2
Reinforcement Learning • Updated
wilt8/ppo-CartPole-v1
Reinforcement Learning • Updated
wilt8/poca-SoccerTwos
Reinforcement Learning • Updated • 5
wilt8/a2c-PandaReachDense-v3
Reinforcement Learning • Updated
wilt8/ppo-Pyramids
Reinforcement Learning • Updated • 11
wilt8/ppo-SnowballTarget
Reinforcement Learning • Updated • 91
wilt8/Reinforce-Pixelcopter-PLE-v0
Reinforcement Learning • Updated
wilt8/Reinforce-CartPole-v1
Reinforcement Learning • Updated
wilt8/dqn-SpaceInvadersNoFrameskip-v4
Reinforcement Learning • Updated • 4
wilt8/q-Taxi-v3
Reinforcement Learning • Updated
wilt8/q-FrozenLake-v1-4x4-noSlippery
Reinforcement Learning • Updated
wilt8/ppo-Huggy
Reinforcement Learning • Updated • 7
wilt8/ppo-LunarLander-v2
Reinforcement Learning • Updated
upvoted an article over 2 years ago
Article
🪆 Introduction to Matryoshka Embedding Models
- +1
tomaarsen, Xenova, osanseviero
• • 215