FlexEvo is introduced, a model-agnostic evolutionary framework that adapts candidates once at inference time from a single target conformation to improve compatibility with alternative natural conformations unseen during adaptation, without retraining the source model or requiring a conformational ensemble.
Qing-Yuan Zeng, Zong-Qi Xu, Ang-Lin Liu et al.· arXiv.org· 0 citations
BIRD is introduced, a self-improving Boundary-Informed Rationale Distillation framework that uses model-specific confusions to locate unresolved local decision boundaries and distills the evidence that resolves these confusions into rationales.
Ang-Lin Liu, Yan-Lin Wu, Rui Chen et al.· 0 citations
Neural State Prediction (NSP), a latent-predictive framework that constrains both the prediction target and the available context, is introduced and jointly designing latent targets and their context offers a promising direction for EEG foundation models that learn from distributed signal structure.
Kieren Yu, Zi-Yang Liu, Chang Huang et al.· 0 citations
Across a European non-interactive multimorbidity benchmark, an Asian interactive multimorbidity benchmark, and an Asian non-interactive cross-guideline benchmark, ATLAS achieves the strongest complete-decision performance among the compared systems.
Zihan Wang, Ang-Lin Liu, Rong Wang et al.· 0 citations
Func-R1 is proposed, which synergistically harmonizes precise visual perception and rigorous logical reasoning and delivers the optimal performance among open-source MLLMs, even surpassing GPT-5 with an 8.4% improvement on MathVerse's function-oriented tasks.
Ming Yin, Xiaohai Wang, Dian Li et al.· Conference on Empirical Meth...· 1 citation
This paper introduces Caduceus, a family of MoE-enhanced foundation models built with a hierarchical pre-training paradigm to jointly integrate biological and natural language, and incorporates a multi-task instruction tuning phase, enabling robust protein parsing and natural language question answering.
Ming-Ze Yin, Yiheng Zhu, Jialu Wu et al.· Proceedings of the 32nd ACM...· 1 citation
EEGBind, an EEG-centric multimodal binding framework for five-class source-level IED classification, is presented and results support EEG-centric multimodal binding as a practical strategy for source-level IED classification.
Muhang Li, Ang-Lin Liu, Xue-Tian Gao et al.· 0 citations
This tutorial presents a systematic overview of this emerging paradigm of tabular foundation models, which treats tables as a common representation that can capture information from tabular data, time series, and graphs within a shared learning framework.
Peng Cui, Xing-Xuan Zhang, Han-Jia Ye et al.· Proceedings of the 32nd ACM...· 0 citations
A comprehensive survey of FedTTA is provided, formalizing its problem setting and establishing a unified taxonomy encompassing three paradigms: i) Federated Initialization and Test Fine-tuning, where the global model serves as a robust prior for local refinement; ii) Federated Shared Backbone and Test Personalized Adap...
Chen Zhang, Ge Su, Huaxia Zhou et al.· International Journal of Com...· 0 citations
This tutorial presents a systematic overview of this emerging paradigm of tabular foundation models, which treats tables as a common representation that can capture information from tabular data, time series, and graphs within a shared learning framework.
Peng Cui, Xingxuan Zhang, Han-Jia Ye et al.· Proceedings of the 32nd ACM...· 0 citations
This paper introduces Caduceus, a family of MoE-enhanced foundation models built with a hierarchical pre-training paradigm to jointly integrate biological and natural language, and incorporates a multi-task instruction tuning phase, enabling robust protein parsing and natural language question answering.
Mingze Yin, Yiheng Zhu, Jialu Wu et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.