The proposed NumCache, which compresses SEC filings into KV caches initialized from numerically dense regions and trained directly on financial QAs, is evaluated, which highlights cache-based retrieval with number-preserving representations as an effective approach for long-context financial QA.
Eftychia Makri, Peiwen Li, Yidong Jiang et al.· Proceedings of the 32nd ACM...· 0 citations
Existing continual-learning methods protect parameters, replayed examples, or Euclidean feature subspaces. When applied to hyperbolic multimodal models, they do not explicitly preserve the Lorentz geometry that jointly encodes within-modality similarity, cross-modal correspondence, and semantic hierarchy; sequential up...
Jia-Hong Liu, Ming Shen, Xiao-Hao Liu et al.· 0 citations
Many scientific datasets, such as molecular conformational ensembles or single-cell tissue measurements, are naturally modeled as meta-distributions: distributions over probability measures on non-Euclidean domains. Existing generative methods largely assume Euclidean geometry and fail to capture this structure. We int...
D. Haviv, E. De Brouwer, Rishabh Anand et al.· 0 citations
The Geometric Space, Architecture and Learning Objective for Large Pre-Trained Models (GALOP) workshop is an accepted half-day KDD 2026 workshop that examines how geometric principles can make large pretrained models more expressive, robust, interpretable, and efficient.
Meng-Lin Yang, Jia-Hong Liu, Lucas Vinh Tran et al.· Proceedings of the 32nd ACM...· 1 citation
On HealMed, performance declined most in low-resource languages, although the size of the gap varied markedly across languages and models, whereas many open-source and medically specialized models showed larger and less consistent gaps.
Yingjian Chen, Fan Gao, Sherry T. Tong 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.
