新方法有望实现神经网络和视频的指数级压缩

报道来源 [4]

1. arXiv cs.AI TIER_1 English(EN) · Andrzej Cichocki, Michal Wietczak · 2026-06-02 04:00

   用于深度神经网络指数压缩的自动可微分非线性张量网络 (ADNTNs)

   arXiv:2606.00130v1 Announce Type: cross Abstract: We study Automatically Differentiable Nonlinear Tensor Networks (ADNTNs), a family of structured weight generators whose compact core tensors are trained end-to-end by reverse-mode automatic differentiation (AD). The approach can …

2. arXiv cs.AI TIER_1 English(EN) · Ravi Dhiman, Andrea Passarella, Mirco Tribastone, Lorenzo Valerio · 2026-06-02 04:00

   通过近似微分等价实现神经网络压缩

   arXiv:2606.01402v1 Announce Type: cross Abstract: Neural network compression is commonly achieved by pruning parameters based on local importance scores, e.g., magnitude-based pruning. We propose a complementary approach that compresses models by aggregating neurons with similar …

3. arXiv cs.CV TIER_1 Italiano(IT) · Jiahao Li, Wenxuan Xie, Zhaoyang Jia, Bin Li, Zongyu Guo, Xiaoyi Zhang, Yan Lu · 2026-06-04 04:00

   超快神经视频压缩

   arXiv:2606.04410v1 Announce Type: new Abstract: While neural video codecs (NVCs) have demonstrated superior compression ratio, their prohibitive computational complexity remains a critical barrier to real-world deployment. This paper introduces a chunk-based coding framework desi…

4. arXiv cs.CV TIER_1 Italiano(IT) · Yan Lu · 2026-06-03 03:38

   超快神经视频压缩

   While neural video codecs (NVCs) have demonstrated superior compression ratio, their prohibitive computational complexity remains a critical barrier to real-world deployment. This paper introduces a chunk-based coding framework designed to significantly improve the rate-distortio…