End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Trainingby Keitaro…
Solid Waste Detection, Monitoring and Mapping in Remote Sensing Images: A Surveyby Piero Fraternali, Luca…
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Spaceby…
FedSiKD: Clients Similarity and Knowledge Distillation: Addressing Non-i.i.d. and Constraints in Federated Learningby Yousef Alsenani,…
How does Your RL Agent Explore? An Optimal Transport Analysis of Occupancy Measure Trajectoriesby Reabetswe…
Sobolev Training for Operator Learningby Namkyeong Cho, Junseung Ryu, Hyung Ju HwangFirst submitted to arxiv…
Exploring the Adversarial Capabilities of Large Language Modelsby Lukas Struppek, Minh Hieu Le, Dominik Hintersdorf,…
Weighted-Sum Gaussian Process Latent Variable Modelsby James Odgers, Ruby Sedgwick, Chrysoula Kappatou, Ruth Misener, Sarah…
When Representations Align: Universality in Representation Learning Dynamicsby Loek van Rossem, Andrew M. SaxeFirst submitted…
ResQuNNs:Towards Enabling Deep Learning in Quantum Convolution Neural Networksby Muhammad Kashif, Muhammad ShafiqueFirst submitted to…