Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learningby Beyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte, Sanjit A.…
SciPIP: An LLM-based Scientific Paper Idea Proposerby Wenxiao Wang, Lihui Gu, Liye Zhang, Yunxiang Luo,…
Improving Uncertainty Quantification in Large Language Models via Semantic Embeddingsby Yashvir S. Grewal, Edwin V.…
Towards Multi-dimensional Explanation Alignment for Medical Classificationby Lijie Hu, Songning Lai, Wenshuo Chen, Hongru Xiao,…
Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustnessby Qi Zhang, Yifei Wang, Jingyi…
Modular Duality in Deep Learningby Jeremy Bernstein, Laker NewhouseFirst submitted to arxiv on: 28 Oct…
HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolationby Yuhan…
Uncovering Capabilities of Model Pruning in Graph Contrastive Learningby Junran Wu, Xueyuan Chen, Shangzhe LiFirst…
FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planningby Nicole Cho, Nishan…
CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activationby Qinsi Wang, Saeed Vahidian,…