Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Modelsby Songtao Liu, Hanjun Dai, Yue…
ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLUby Qi Qiu,…
Iteration Head: A Mechanistic Study of Chain-of-Thoughtby Vivien Cabannes, Charles Arnal, Wassim Bouaziz, Alice Yang,…
Causal Discovery with Fewer Conditional Independence Testsby Kirankumar Shiragur, Jiaqi Zhang, Caroline UhlerFirst submitted to…
CAFO: Feature-Centric Explanation on Time Series Classificationby Jaeho Kim, Seok-Ju Hahn, Yoontae Hwang, Junghye Lee,…
Learning the Target Network in Function Spaceby Kavosh Asadi, Yao Liu, Shoham Sabach, Ming Yin,…
EMOE: Expansive Matching of Experts for Robust Uncertainty Based Rejectionby Yunni Qu, James Wellnitz, Alexander…
Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapyby Riqiang Gao, Florin C. Ghesu, Simon Arberet,…
Neural Green’s Operators for Parametric Partial Differential Equationsby Hugo Melchers, Joost Prins, Michael AbdelmalikFirst submitted…
Understanding Stochastic Natural Gradient Variational Inferenceby Kaiwen Wu, Jacob R. GardnerFirst submitted to arxiv on:…