Explainable Concept Generation through Vision-Language Preference Learningby Aditya Taparia, Som Sagar, Ransalu SenanayakeFirst submitted to…
Knowledge-Aware Conversation Derailment Forecasting Using Graph Convolutional Networksby Enas Altarawneh, Ameeta Agrawal, Michael Jenkin, Manos…
A Law of Next-Token Prediction in Large Language Modelsby Hangfeng He, Weijie J. SuFirst submitted…
Reinforcement Learning for Causal Discovery without Acyclicity Constraintsby Bao Duong, Hung Le, Biwei Huang, Thin…
Uncovering Biases with Reflective Large Language Modelsby Edward Y. ChangFirst submitted to arxiv on: 24…
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reductionby Xinwei Zhang, Zhiqi Bu,…
Data Augmentation for Continual RL via Adversarial Gradient Episodic Memoryby Sihao Wu, Xingyu Zhao, Xiaowei…
LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMsby Chansung Park,…
MPruner: Optimizing Neural Network Size with CKA-Based Mutual Information Pruningby Seungbeom Hu, ChanJun Park, Andrew…
Disentangled Generative Graph Representation Learningby Xinyue Hu, Zhibin Duan, Xinyang Liu, Yuxin Li, Bo Chen,…