Uplift modeling with continuous treatments: A predict-then-optimize approachby Simon De Vos, Christopher Bockel-Rickermann, Stefan Lessmann,…
Evaluating Adversarial Attacks on Traffic Sign Classifiers beyond Standard Baselinesby Svetlana Pavlitska, Leopold Müller, J.…
GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuningby Abdessalam Ed-dib, Zhanibek Datbayev, Amine Mohamed AboussalahFirst…
Towards modeling evolving longitudinal health trajectories with a transformer-based deep learning modelby Hans Moen, Vishnu…
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionariesby Junhyuck Kim, Jongho Park,…
FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learningby Prajwal Koirala,…
Efficient Reinforcement Learning for Optimal Control with Natural Imagesby Peter N. LoxleyFirst submitted to arxiv…
SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimizationby Kwangryeol Park, Seulki LeeFirst submitted to arxiv on:…
Radiology Report Generation via Multi-objective Preference Optimizationby Ting Xiao, Lei Shi, Peng Liu, Zhe Wang,…
Neural Interactive Proofsby Lewis Hammond, Sam Adam-DayFirst submitted to arxiv on: 12 Dec 2024CategoriesMain: Artificial…