2 papers
cs.CV2026
RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images Understanding
Gaozhi Zhou, Hu He, Peng Shen +8
Reinforcement learning (RL) post-training substantially improves remote sensing vision-language models (RS-VLMs). However, when handling complex remote sensing imagery (RSI) requir…
cs.AI2024
STDCformer: A Transformer-Based Model with a Spatial-Temporal Causal De-Confounding Strategy for Crowd Flow Prediction
Silu He, Peng Shen, Pingzhen Xu +2
Existing works typically treat spatial-temporal prediction as the task of learning a function to transform historical observations to future observations. We further decompose…