works on
evidence routing 1high-resolution visual question answering 1memory efficiency 1multimodal large language models 1single-pass inference 1

From the 1 of 5 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models

Yidong Wang, Yan Zhan, Ziteng Feng +16

Reward models are a bottleneck for reinforcement learning in embodied AI. Long-horizon robotic manipulation requires scalable vision feedback beyond handcrafted rewards or task-spe…