conftrace_

parameter prior

4 papers

Explore in graph

Co-occurring keywords

cross-modal knowledge distillation (10) descriptive adequacy (1) 1-bit convolutional network (1) full-precision kernel (1) prior predictive (3) bayesian optimization (624) gradient compression (78) language model (4599) lossless compression (41) arithmetic coding (8)

Papers

Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models NIPS 2024
Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge CVPR 2020
Bayesian Optimized 1-Bit CNNs ICCV 2019
Measuring model complexity with the prior predictive NIPS 2009