Freeform Preference Learning trains language-conditioned multi-axis reward models from human pairwise preferences to produce steerable and compositional robot policies that outperform sparse and binary-preference baselines by 38 percentage points.
Don’t Start From Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Derives optimal inference-time guidance for stochastic interpolant policies via Kolmogorov equation analysis, enabling reactive streaming robot control with training-free and training-based mechanisms.
InCoM achieves 23-28% higher success rates in mobile manipulation tasks by inferring motion intent for adaptive perception and decoupling base-arm action generation.
citing papers explorer
-
Freeform Preference Learning for Robotic Manipulation
Freeform Preference Learning trains language-conditioned multi-axis reward models from human pairwise preferences to produce steerable and compositional robot policies that outperform sparse and binary-preference baselines by 38 percentage points.
-
Guided Streaming Stochastic Interpolant Policy
Derives optimal inference-time guidance for stochastic interpolant policies via Kolmogorov equation analysis, enabling reactive streaming robot control with training-free and training-based mechanisms.
-
InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation
InCoM achieves 23-28% higher success rates in mobile manipulation tasks by inferring motion intent for adaptive perception and decoupling base-arm action generation.