Summary of Hamiltonian Monte Carlo on Relu Neural Networks Is Inefficient, by Vu C. Dinh et al.
Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficientby Vu C. Dinh, Lam Si Tung…
Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficientby Vu C. Dinh, Lam Si Tung…
The Impact of Inference Acceleration on Bias of LLMsby Elisabeth Kirsten, Ivan Habernal, Vedant Nanda,…
Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Mergingby Li Shen, Anke Tang,…
Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformersby Shaobo Wang, Hongxuan Tang, Mingyang Wang, Hongrui…
On the Robustness of Adversarial Training Against Uncertainty Attacksby Emanuele Ledda, Giovanni Scodeller, Daniele Angioni,…
Meta-Learning for Speeding Up Large Model Inference in Decentralized Environmentsby Yuzhe Yang, Yipeng Du, Ahmad…
ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inferenceby Hanshi Sun, Li-Wen Chang, Wenlei…
AiSciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classificationby Brendan Hogan, Anmol…
Trustworthiness of Stochastic Gradient Descent in Distributed Learningby Hongyang Li, Caesar Wu, Mohammed Chadli, Said…
Self-Supervised Learning and Opportunistic Inference for Continuous Monitoring of Freezing of Gait in Parkinson’s Diseaseby…