FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizersby Joshua Nathaniel Williams, J.…
Interventional Causal Structure Discovery over Graphical Models with Convergence and Optimality Guaranteesby Qiu Chengbo, Yang…
Performance Metric for Multiple Anomaly Score Distributions with Discrete Severity Levelsby Wonjun Yi, Yong-Hwa Park,…
Advancing Molecular Machine (Learned) Representations with Stereoelectronics-Infused Molecular Graphsby Daniil A. Boiko, Thiago Reschützegger, Benjamin…
Knowledge-Aided Semantic Communication Leveraging Probabilistic Graphical Modelingby Haowen Wan, Qianqian Yang, Jiancheng Tang, Zhiguo shiFirst…
Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPsby Kevin Tan, Wei Fan, Yuting…
AExGym: Benchmarks and Environments for Adaptive Experimentationby Jimmy Wang, Ethan Che, Daniel R. Jiang, Hongseok…
How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regressionby…
BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Modelsby Yupeng Chang, Yi…
Activation degree thresholds and expressiveness of polynomial neural networksby Bella Finkel, Jose Israel Rodriguez, Chenxi…