23 papers
Socialized Division and Collaboration: Rethinking Class-Incremental Learning under Optimization Conflicts
Xinjie Yao, Zhihe Fan, Yunqi Zhu +6
Class-incremental learning is commonly instantiated as a single-model paradigm, where a unified model sequentially adapts to an unbounded stream of sessions. While effective under…
DynCur-Geo: Dynamic Curiosity Reward Shaping for Multimodal Active Geo-Localization
Yiming Sun, Yang Zhang, Pengfei Zhu
Active geo-localization enables low-altitude UAVs to search for specified targets from limited local aerial observations, supporting time-sensitive applications such as search and…
Towards a new paradigm of scientific discovery with socialized artificial intelligence
Xinjie Yao, Xingxin Xu, Xiyuan Gao +21
Scientific discovery has advanced through successive transformations in the organization of knowledge. Observation and experimentation established the empirical foundations of scie…
Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning
Haifang Cao, Yu Wang, Timing Li +2
Graph-structured data typically exhibits complex topological heterogeneity, making it difficult to model accurately within a single Riemannian manifold. While emerging mixed-curvat…
Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion
Timing Li, Bing Cao, Jiahe Feng +3
Image fusion synthesizes complementary information from multiple sources, mitigating the inherent limitations of unimodal imaging systems. Accurate image registration is essential…
RGBX-R1: Visual Modality Chain-of-Thought Guided Reinforcement Learning for Multimodal Grounding
Jiahe Wu, Bing Cao, Qilong Wang +3
Multimodal Large Language Models (MLLM) are primarily pre-trained on the RGB modality, thereby limiting their performance on other modalities, such as infrared, depth, and event da…