7 papers · ranked by Valyu relevance
Seonghwan Seo, Hyeongwoo Kim, Seokhyun Moon, Woo Youn Kim
Protein language models (PLMs) trained on evolutionary sequences learn representations that encode protein structure, enabling direct structure prediction without multiple-sequence alignments (MSAs). Here we present the Atlas model family, an open and trainable system spanning protein language modeling, monomer…
Yi Ren, Zimei Chen, Hayden Deans, Ying Nian Wu + 1 more
Extensive studies suggest the brain performs Bayesian inference to infer the latent world states. It is a fundamental neuroscience question that how canonical recurrent neural circuits in the brain implement Bayesian inference. Many existing theoretical studies focused on how the recurrent circuits compute the…
Hao Ding, Nannan Wu, Tianyi Qiu
DNA foundation models such as Evo2 7B adopt hybrid Hyena/attention architectures (Striped-Hyena2) whose single-stream autoregressive decoding is bounded by weight bandwidth at ∼45 tok/s. Speculative decoding on such hybrids faces a systems problem that prior SSM work solves only partially: after a draft is verified…
Yuesong Wu, Haohao Su, Yuehua Cui
Cell-cell communication (CCC) is essential for maintaining tissue organization and driving biological progression, yet its inference from transcriptomic data has long been limited by the absence of spatial context. Advances in spatial transcriptomics (ST) now enable mechanistically grounded analyses of CCC by…
Junjie Yao, Zhongxu Li, Cuiping Wang, Junyu Wu + 3 more
A motion control strategy based on multi-source heterogeneous motion information fusion and motion decoupling parallel washout algorithm (WA) is proposed for the control of a rehabilitation robot designed for stroke-related balance disorders. The robot features a serial-parallel hybrid structure and humanoid gait…
Yuqiao Liu, Siyu Yi, Hengchuang Yin, Wei Ju
Single-cell RNA sequencing profiles cellular heterogeneity at atlas scale, making automated annotation essential. However, target datasets often contain novel cell types missing from incomplete references. We present scOLAR, an ontology-guided open-set framework that learns prototypes over the Cell Ontology and uses…
Dianzhuo Wang, Qian Xu, Arjun Banerjee, Rishi Jain + 7 more
Inferring biological function from experimental data is central to understanding emerging pathogens and developing effective countermeasures, yet interpreting these data remains slow and expert-intensive. AI agents could help accelerate this process by reasoning across sequence, structural, and biophysical evidence. We…