Adaptive Active Inference Agents for Heterogeneous and Lifelong Federated Learningby Anastasiya Danilenka, Alireza Furutanpey, Victor…
Training on Fake Labels: Mitigating Label Leakage in Split Learning via Secure Dimension Transformationby Yukun…
ALVIN: Active Learning Via INterpolationby Michalis Korakakis, Andreas Vlachos, Adrian WellerFirst submitted to arxiv on:…
Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Modelsby Qin Liu, Chao Shang, Ling Liu,…
Path-minimizing Latent ODEs for improved extrapolation and inferenceby Matt L. Sampson, Peter MelchiorFirst submitted to…
Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Modelsby Reza Abbasi, Sernam…
Unveiling Molecular Secrets: An LLM-Augmented Linear Model for Explainable and Calibratable Molecular Property Predictionby Zhuoran…
QEFT: Quantization for Efficient Fine-Tuning of LLMsby Changhun Lee, Jun-gyu Jin, Younghyun Cho, Eunhyeok ParkFirst…
Efficiently Scanning and Resampling Spatio-Temporal Tasks with Irregular Observationsby Bryce Ferenczi, Michael Burke, Tom DrummondFirst…
Why pre-training is beneficial for downstream classification tasks?by Xin Jiang, Xu Cheng, Zechao LiFirst submitted…