19 citations · 20 across the 4 of their papers we have counts for
4 papers
Learning from Active Human Involvement through Proxy Value Propagation
Zhenghao Peng, Wenjie Mo, Chenda Duan +2
Learning from active human involvement enables the human subject to actively intervene and demonstrate to the AI agent during training. The interaction and corrective feedback from…
ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling
Quanyi Li, Zhenghao Peng, Lan Feng +4
Large-scale driving datasets such as Waymo Open Dataset and nuScenes substantially accelerate autonomous driving research, especially for perception tasks such as 3D detection and…
A Causal View of Entity Bias in (Large) Language Models
Fei Wang, Wenjie Mo, Yiwei Wang +2
Entity bias widely affects pretrained (large) language models, causing them to rely on (biased) parametric knowledge to make unfaithful predictions. Although causality-inspired met…
Feature Tracks are not Zero-Mean Gaussian
Stephanie Tsuei, Wenjie Mo, Stefano Soatto
In state estimation algorithms that use feature tracks as input, it is customary to assume that the errors in feature track positions are zero-mean Gaussian. Using a combination of…