ReMoT: Reinforcement Learning with Motion Contrast Triplets

Cong Wan, Zeyu Guo, Jiangyang Li +5

Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI

Kairos Team, Fei Wang, Shan You +21

A novel sentence embedding based topic detection method for micro-blog

Cong Wan, Shan Jiang, Cuirong Wang +4

Trajectory-Diversity-Driven Robust Vision-and-Language Navigation

Jiangyang Li, Cong Wan, SongLin Dong +4

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs

Jianchao Zhao, Huoren Yang, Yusong Hu +6

DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

Cong Wan, Zeyu Guo, Zijian Cai +6

CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation

Xiangyang Luo, Ye Zhu, Yunfei Liu +5

Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning

Cong Wan, Ying He, Zhongzhan Huang +1

Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models

Cong Wan, Yuhang He, Xiang Song +1

ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs

Jiangyang Li, Cong Wan, Changjie Wu +8

Grid: Omni Visual Generation

Cong Wan, Xiangyang Luo, Hao Luo +7

CoRe: A Comprehensive Framework for Cross-Image Comparative Reasoning in Vision-Language Models

Lin Peng, Cong Wan, Zeyu Guo +2

The paper introduces CoRe, a framework that improves vision-language models' ability to perform fine-grained cross‑image comparative reasoning by providing a large triplet‑based da…

SI based disease model over signed network

Cong Wan, Cong Wang, Yanxia Lv