AI & ML interests
None defined yet.
Recent Activity
Papers
LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
Dream
MetaWorld
-
RLinf/RLinf-OpenSora-LIBERO-Spatial
1B • Updated • 15 -
RLinf/RLinf-OpenVLAOFT-LIBERO-90-Base-Lora
Reinforcement Learning • 8B • Updated • 35 -
RLinf/RLinf-OpenVLAOFT-GRPO-LIBERO-object
Reinforcement Learning • 8B • Updated • 15 -
RLinf/RLinf-OpenVLAOFT-GRPO-LIBERO-goal
Reinforcement Learning • 8B • Updated • 14
RL-based co-training in RLinf
-
RLinf/RLinf-Pi05-RLCo-PandaPutOnPlateInScene25DigitalTwin-V1-SFT
4B • Updated -
RLinf-Co: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
Paper • 2602.12628 • Published • 12 -
RLinf/RLCo-Example-Mix-Data
Viewer • Updated • 3.1k • 18 -
RLinf/RLCo-Example-Real-Data
Viewer • Updated • 100 • 124
WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
-
RLinf/RLinf-OpenVLAOFT-LIBERO-130-Base-Lora
Reinforcement Learning • 8B • Updated • 1.65k -
RLinf/RLinf-OpenVLAOFT-ManiSkill-Base-Main
8B • Updated • 102 -
RLinf/RLinf-OpenVLAOFT-LIBERO-90-Base-Lora
Reinforcement Learning • 8B • Updated • 35 -
RLinf/RLinf-OpenVLAOFT-LIBERO-130
Reinforcement Learning • 8B • Updated • 20 • 3
Dream
MetaWorld
RL-based co-training in RLinf
-
RLinf/RLinf-Pi05-RLCo-PandaPutOnPlateInScene25DigitalTwin-V1-SFT
4B • Updated -
RLinf-Co: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
Paper • 2602.12628 • Published • 12 -
RLinf/RLCo-Example-Mix-Data
Viewer • Updated • 3.1k • 18 -
RLinf/RLCo-Example-Real-Data
Viewer • Updated • 100 • 124
WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
-
RLinf/RLinf-OpenVLAOFT-LIBERO-130-Base-Lora
Reinforcement Learning • 8B • Updated • 1.65k -
RLinf/RLinf-OpenVLAOFT-ManiSkill-Base-Main
8B • Updated • 102 -
RLinf/RLinf-OpenVLAOFT-LIBERO-90-Base-Lora
Reinforcement Learning • 8B • Updated • 35 -
RLinf/RLinf-OpenVLAOFT-LIBERO-130
Reinforcement Learning • 8B • Updated • 20 • 3
-
RLinf/RLinf-OpenSora-LIBERO-Spatial
1B • Updated • 15 -
RLinf/RLinf-OpenVLAOFT-LIBERO-90-Base-Lora
Reinforcement Learning • 8B • Updated • 35 -
RLinf/RLinf-OpenVLAOFT-GRPO-LIBERO-object
Reinforcement Learning • 8B • Updated • 15 -
RLinf/RLinf-OpenVLAOFT-GRPO-LIBERO-goal
Reinforcement Learning • 8B • Updated • 14