Skip to content
RobotWorld
← Back to Videos

CoRL 2026 paper removes undesired modes after BC training

Loading video
Loading video

The CoRL 2026 paper introduces Behavior Uncloning to remove undesired behavior modes after behavior cloning, without inference-time steering, improving safe human-robot interaction such as knife handover.

CoRLBehavior UncloningResearchBehavioral cloningHuman-robot interactionSafetyRobot Learning
Category: research
Author: @zhiwen_fan_
Date: 2026-09-04T00:00:00
Duration: 76.8s
Source: https://x.com/zhiwen_fan_/status/2095942241269272672

Related Videos

HARBOR goes from one prompt to a trained robot policy
3:46

HARBOR goes from one prompt to a trained robot policy

@softraeh · 742 views · 2026-09-04
HarborCoRL
WARP-RM Filters Productive Moments in T-Shirt Folding Demos
0:50

WARP-RM Filters Productive Moments in T-Shirt Folding Demos

@uynitsuj · 787 views · 2026-06-30
Robot LearningReward Model
Workshop: making real-world RL practical
0:45

Workshop: making real-world RL practical

@yigitkkorkmaz · 838 views · 2026-08-31
RLReinforcement Learning
MessyMem: Persistent Spatial Memory for Robots
0:48

MessyMem: Persistent Spatial Memory for Robots

@anuvabanwasi · 908 views · 2026-09-16
Persistent MemoryMobile Manipulation
Lumos NexCore: End-to-End Robot Skill Platform
0:56

Lumos NexCore: End-to-End Robot Skill Platform

@LumosRobotics · 683 views · 2026-09-15
Robot SkillsRobot Learning
Odyssey-3: A Foundation World Model for Physical Agents
1:37

Odyssey-3: A Foundation World Model for Physical Agents

@odysseyml · 1.2k views · 2026-09-15
World ModelsFoundation Models

As an Amazon Associate, we earn from qualifying purchases.