pith. sign in

Video prediction models as rewards for reinforcement learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.RO 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning

cs.RO · 2026-02-11 · unverdicted · novelty 6.0

LifeLong-RFT applies chunking-level on-policy reinforcement learning with Quantized Action Consistency Reward, Continuous Trajectory Alignment Reward, and Format Compliance Reward to fine-tune VLA models, achieving a 22% average success rate gain over supervised fine-tuning on the LIBERO benchmark's

citing papers explorer

Showing 1 of 1 citing paper.

  • Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning cs.RO · 2026-02-11 · unverdicted · none · ref 17

    LifeLong-RFT applies chunking-level on-policy reinforcement learning with Quantized Action Consistency Reward, Continuous Trajectory Alignment Reward, and Format Compliance Reward to fine-tune VLA models, achieving a 22% average success rate gain over supervised fine-tuning on the LIBERO benchmark's