23 papers
SUMO: Segment and Track Any Motion with Nonlinear State Space Models
Kexin Tian, Sixu Li, Keshu Wu +2
Visual Object Tracking (VOT) and Moving Object Segmentation (MOS) are two fundamental tasks in computer vision that involve both spatial and temporal object dynamics. Existing meth…
KANMixer: a minimal KAN-centered mixer for long-term time series forecasting
Lingyu Jiang, Dengzhe Hou, Yuping Wang +9
Long-term time series forecasting (LTSF) underpins critical applications from energy management to weather prediction, yet achieving reliable multi-step-ahead accuracy remains chal…
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
Zhiwen Fan, Jian Zhang, Renjie Li +15
The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has motivated extending these models to understand 3D scenes, aiming for human-like visual-spatial…
Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models
Keshu Wu, Chenchen Kuai, Zihao Li +6
Retrieval-augmented generation (RAG) enhances large language models by grounding outputs in retrieved knowledge. However, existing RAG methods including graph- and hypergraph-based…
NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks
Fangzhou Lin, Yuping Wang, Yuliang Guo +7
Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the…
AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving
Shuo Xing, Hongyuan Hua, Xiangbo Gao +10
Recent advancements in large vision language models (VLMs) tailored for autonomous driving (AD) have shown strong scene understanding and reasoning capabilities, making them undeni…