activity
20242026
collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward

Zile Zhou, Huining Yuan, Weichen Zhang +2

Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable…

cs.CV2026

Uncertainty-Aware World Model for Aerial Image-Goal Navigation

Deyi Zhu, Haoyu Fan, Yinan Zhu +4

Aerial image-goal navigation requires an unmanned aerial vehicle (UAV) to reach a target location specified by a goal image. Existing world-model-based methods rank candidate traje…

cs.CV2026

TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment

Yu Meng, Xiangyang Luo, Letian Li +5

Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generate…

cs.CV2026

iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework

Jianjie Fang, Yingshan Lei, Qin Wan +8

Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, re…

cs.CV2025

PhysFire-WM: A Physics-Informed World Model for Emulating Fire Spread Dynamics

Nan Zhou, Huandong Wang, Jiahao Li +4

Fine-grained fire prediction plays a crucial role in emergency response. Infrared images and fire masks provide complementary thermal and boundary information, yet current methods…

cs.CV2025

FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting

Nan Zhou, Huandong Wang, Jiahao Li +5

Fine-grained wildfire spread prediction is crucial for enhancing emergency response efficacy and decision-making precision. However, existing research predominantly focuses on coar…