Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformersby Haoran You, Connelly Barnes,…
Transformer-based toxin-protein interaction analysis prioritizes airborne particulate matter components with potential adverse health effectsby Yan…
Lillama: Large Language Models Compression via Low-Rank Feature Distillationby Yaya Sy, Christophe Cerisara, Irina IllinaFirst…
Paraformer: Parameterization of Sub-grid Scale Processes Using Transformersby Shuochen Wang, Nishant Yadav, Auroop R. GangulyFirst…
MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insightsby Jingjing Hu, Dan Guo, Zhan Si,…
Spatial-Temporal Knowledge Distillation for Takeaway Recommendationby Shuyuan Zhao, Wei Chen, Boyan Shi, Liyong Zhou, Shuohao…
VSFormer: Value and Shape-Aware Transformer with Prior-Enhanced Self-Attention for Multivariate Time Series Classificationby Wenjie Xi,…
HashEvict: A Pre-Attention KV Cache Eviction Strategy using Locality-Sensitive Hashingby Minghui Liu, Tahseen Rabbani, Tony…
GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learningby Jianqing Liang, Xinkai Wei, Min Chen, Zhiqiang…
Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics with Temporal Fusion…