While deep learning models have achieved unprecedented success in short-to-medium-range weather forecasting, they universally suffer from error accumulation, spectral decay, and climate drift during long-horizon autoregressive rollouts. We argue that this stems from a fundamental paradigm flaw: treating forecasting as...
Tan-Da Li, Lu-Jie Yin, Yu-Qi Li et al.· Proceedings of the 35th ACM...· 0 citations
As automated research is increasingly adopted for writing papers, automated review has become a critical link between paper generation and quality control. However, existing methods largely rely on single-model feedback or simple review aggregation, failing to explicitly model expert responsibilities or collective deli...
Junkai Zhou, Jia-Jian Wu, Zhao-Yi Zhang et al.· 0 citations
Recent 3D large multimodal models (3D-LMMs) rely on a visual bottleneck to compress complex 3D scene evidence into a limited number of visual tokens compatible with large language models (LLMs). Current visual bottlenecks, however, often passively compress heterogeneous 3D evidence into a homogeneous object-centric tok...
Xiang-Qi Li, Li-Bo Huang, Jia-Rui Zhao et al.· 0 citations
Large-scale video diffusion models (V-DMs) have achieved remarkable text-to-video generation quality, yet their massive computational complexity makes deployment costly. Post-Training Quantization (PTQ) offers an appealing route to accelerate inference without retraining, but existing diffusion PTQ methods remain fragi...
Wei-Lun Feng, Chuan-Guang Yang, Haotong Qin et al.· IEEE Transactions on Pattern...· 4 citations
P predictive Prompting (PrePrompt) is proposed, a novel CIL framework that circumvents correlation-based limitations by leveraging the inherent classification ability of pre-trained models to predict task-specific prompts and decomposes CIL into a two-stage prediction process: task-specific prompt prediction followed b...
Li-Bo Huang, Xiang-Qi Li, Jia-Rui Zhao et al.· Proceedings of the 32nd ACM...· 4 citations
A unified taxonomy that categorized existing methods into three primary paradigms: Interactive Generation, Interactive Editing, and Embodied Interaction is proposed that categorized existing methods into three primary paradigms and discussed their advantages and limitations.
Yu-Qi Li, Si-Wei Meng, Chuan-Guang Yang et al.· Proceedings of the Thirty-Fi...· 40 citations· ⚡1
DA-Nav is proposed, a Direction-Aware vision-language Navigation framework that reformulates navigation as a discrete spatial grounding problem on the egocentric 2D image plane, outperforming existing State-of-The-Art (SoTA) methods while maintaining a substantially stronger recovery capability.
Ye Yuan, Kehan Chen, Xinqiang Yu et al.· arXiv.org· 0 citations
Prompt-based learning has emerged as a promising paradigm for Class Incremental Learning (CIL), enabling pre-trained models to adapt efficiently to open-world scenarios. Existing methods often employ correlation-based strategies, where an image's feature serves as a query to retrieve the most relevant key prompts, with...
Libo Huang, Xiangqi Li, Jiarui Zhao et al.· Proceedings of the 32nd ACM...· 0 citations
RSIAT significantly outperforms state-of-the-art methods in both performance and parameter efficiency, achieving superior stability–plasticity trade-offs with minimal trainable parameters.
Jiarui Zhao, Libo Huang, Xiangqi Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.