Unified atomistic modeling has the potential to accelerate discovery in chemistry, materials science, and biology by bridging data-rich chemical domains and data-scarce biological contexts. However, existing generative approaches to atomistic modeling remain highly specialized to scientific disciplines (chemistry vs. b...
M. Cretu, A. Abrudan, Antonia Panescu et al.· 0 citations
Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoning ability is reflected in internal organization. Inspired by neuroscience findings linking higher intelligence to stronger small-world organization in functional brain networks, we investigate small-...
Zheng Huang, Sansheng Cao, En-Pei Zhang et al.· 0 citations
Hyperbolic geometry has recently emerged as a powerful representation space for multimodal learning, as it naturally captures hierarchical semantic structure across modalities. Despite this progress, how such representations behave under continual learning poses fundamentally different challenges that remain underexplo...
Jia-Hong Liu, Ming Shen, Xiao-Hao Liu et al.· 2 citations
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, Yi-Dong Jiang et al.· Proceedings of the 32nd ACM...· 0 citations
Across a unified 16-task classification-retrieval stream with three hyperbolic backbones, HMCL improves final performance and backward transfer over sequential fine-tuning and four continual-learning baselines; HMCL-CA gives the highest Overall score on every backbone.
Jia-Hong Liu, Ming Shen, Xiao-Hao Liu et al.· 0 citations
Riemannian Wasserstein Entropic Flow Matching (RWEFM) is introduced, a generative framework on the Wasserstein space of a Riemannian manifold that can generate whole single-cell samples in hyperspherical latent spaces and protein conformational ensembles on the torus by respecting the intrinsic geometry of the data.
D. Haviv, E. De Brouwer, Rishabh Anand et al.· 0 citations
This work proposes LabAgent, a reproduce and discovery harness tailored for a lab's continuous work that ranks first over commercial generalist agents in every domain, and demonstrates accurate reproduction of a published figure.
Lei Liu, Yi-Kun Zhang, Jia-Lin Chen et al.· 0 citations
This work introduces Kalman Delta Networks (KDNs), a family of linear-attention models that explicitly track memory uncertainty to guide each update, and derives Diagonal KDN and Isotropic KDN, which retain one uncertainty value per key channel and per head, respectively.
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
This work proposes FlatLand, a novel personalized federated learning method that embeds different clients'data in tailored Lorentz space of hyperbolic geometry, and develops a parameter decoupling strategy that separates heterogeneous information from common knowledge, enabling direct aggregation without requiring clie...
Jia-Hong Liu, B. RamSamarthB, Xinyu Fu et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.