Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformersby Haowei Ni, Shuchen Meng,…
Hierarchical Associative Memory, Parallelized MLP-Mixer, and Symmetry Breakingby Ryo Karakida, Toshihiro Ota, Masato TakiFirst submitted…
Rethinking Spatio-Temporal Transformer for Traffic Prediction:Multi-level Multi-view Augmented Learning Frameworkby Jiaqi Lin, Qianqian RenFirst submitted…
Crossfusor: A Cross-Attention Transformer Enhanced Conditional Diffusion Model for Car-Following Trajectory Predictionby Junwei You, Haotian…
Transcoders Find Interpretable LLM Feature Circuitsby Jacob Dunefsky, Philippe Chlenski, Neel NandaFirst submitted to arxiv…
Delay Embedding Theory of Neural Sequence Modelsby Mitchell Ostrow, Adam Eisen, Ila FieteFirst submitted to…
Transcendence: Generative Models Can Outperform The Experts That Train Themby Edwin Zhang, Vincent Zhu, Naomi…
Compact Proofs of Model Performance via Mechanistic Interpretabilityby Jason Gross, Rajashree Agrawal, Thomas Kwa, Euan…
Words in Motion: Extracting Interpretable Control Vectors for Motion Transformersby Omer Sahin Tas, Royden WagnerFirst…
SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learningby Kaidi Li, Tianmeng Yang, Min Zhou,…