Deep Learning
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
This raises a challenging research question: How can we keep improving the systems when their capabilities have surpassed the levels of humans?
Training deep learning based denoisers without ground truth data
Shakarim Soltanayev, Se Young Chun
Neural Information Processing Systems http://nips.cc/
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
Key attributes (cf. Figure 1) include the challenging task of classifying doppelganger animals,
Can We Gain More from Orthogonality Regularizations in Training Deep Networks?
Nitin Bansal, Xiaohan Chen, Zhangyang Wang
Neural Information Processing Systems http://nips.cc/
Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin, Dmitry P. Vetrov, Andrew G. Wilson
The loss functions of deep neural networks are complex and their geometric properties are not well understood.
Optimal Transport-Guided Conditional Score-Based Diffusion Model (Appendix) Xiang Gu1, Liwei Y ang
We next explain the rationality of the resampling-by-compatibility presented in Sect. We first i) prove Eq. For Assumption (9), L( π, u, v) is strongly convex as proved in [5]. Eq. (A-19), we have E The codes are in pytorch [7]. The learning rate is 1e-5.
Exploring Token Pruning in Vision State Space Models
We first introduce a pruning-aware hidden state alignment method to stabilize the neighborhood of remaining tokens for performance enhancement.