3 papers
cs.CV2026
DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models
Chenyang Li, Jieyuan Liu, Bin Li +5
Vision-Language Action (VLA) models have shown remarkable progress in robotic manipulation by leveraging the powerful perception abilities of Vision-Language Models (VLMs) to under…
cs.LG2026
Physics-Informed Gaussian Process Regression for the Constitutive Modeling of Concrete: A Data-Driven Improvement to Phenomenological Models
Chenyang Li, Himanshu Sharma, Youcai Wu +3
Understanding and modeling the constitutive behavior of concrete is crucial for civil and defense applications, yet widely used phenomenological models such as Karagozian \& Case c…
astro-ph.EP2025
Massive Retrograde Moons May Survive During Different Hot Jupiters' Migration Scenario
Yangjun Pu, Chenyang Li, Bohang Zhu
Searching for exomoons is attempted via Kepler and TESS, but none is confirmed. Theoretically, similar with Jupiter, the gas giants are possible to generate moons. However, HJs whi…