MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependenceby Hongduan Tian, Feng Liu,…
Causal Contextual Bandits with Adaptive Contextby Rahul Madhavan, Aurghya Maiti, Gaurav Sinha, Siddharth BarmanFirst submitted…
Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inferenceby Hao Mark Chen, Wayne Luk,…
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attackby Tiansheng Huang, Sihao…
Watermarking Counterfactual Explanationsby Hangzhi Guo, Firdaus Ahmed Choudhury, Tinghua Chen, Amulya YadavFirst submitted to arxiv…
Rejection via Learning Density Ratiosby Alexander Soen, Hisham Husain, Philip Schulz, Vu NguyenFirst submitted to…
The Unified Balance Theory of Second-Moment Exponential Scaling Optimizers in Visual Tasksby Gongyue Zhang, Honghai…
MC-GTA: Metric-Constrained Model-Based Clustering using Goodness-of-fit Tests with Autocorrelationsby Zhangyu Wang, Gengchen Mai, Krzysztof Janowicz,…
From Learning to Optimize to Learning Optimization Algorithmsby Camille Castera, Peter OchsFirst submitted to arxiv…
Adaptive debiased SGD in high-dimensional GLMs with streaming databy Ruijian Han, Lan Luo, Yuanhang Luo,…