English(EN)Dynamic Compression in Recurrent Networks
AI研究探索模型和数据的先进压缩技术
作者PulseAugur 编辑部·[6 个来源]·
研究人员正在探索机器学习模型和数据的先进压缩技术。曼彻斯特大学的一项研究调查了基于机器学习的数据压缩的环境可持续性，将训练和推理的碳足迹与存储减少带来的节省进行了比较。另一篇论文介绍了循环神经网络的动态压缩，允许模型选择性地重新访问过去的信息以减小状态大小并提高效率。此外，一个名为BRIDGE 的新框架将模型压缩重新表述为边界搜索问题，使模型能够从性能崩溃中恢复并在不同架构中扩展压缩限制。最后，正在进行关于抗损耗学习图像压缩的研究，以提高在丢包情况下的鲁棒性，特别是在具有挑战性的通信环境中的应用。
AI
arXiv:2608.19994v1 Announce Type: new Abstract: We summarise the outcome of two summer internship projects based at the University of Manchester, focused on the break-even point in terms of environmental sustainability for ML-based data compression algorithms. Using the example o…
arXiv cs.LG
TIER_1English(EN)·Jyothish Pari, Ryan Bahlous-Boldi, Pulkit Agrawal·
arXiv:2608.17896v1 Announce Type: new Abstract: Recurrent models process long contexts efficiently by compressing their history into a fixed-size state, but modern architectures typically do so in a single causal pass over the sequence. Each input must therefore be compressed bef…
Recurrent models process long contexts efficiently by compressing their history into a fixed-size state, but modern architectures typically do so in a single causal pass over the sequence. Each input must therefore be compressed before the model knows how it will later be used, f…
arXiv:2608.15113v1 Announce Type: cross Abstract: Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings. However, the high representational capacity endowed by deep neural networks (DNNs) comes at the expense of increased …
arXiv cs.LG
TIER_1English(EN)·Zhaocen Liu, Satvik Praveen, Yi Sheng·
arXiv:2608.16010v1 Announce Type: new Abstract: Model compression is critical for deploying networks on resource-constrained edge devices. While pruning-based methods can significantly reduce model size, they often suffer from abrupt performance collapse beyond a sparsity thresh-…
Learned image compression (LIC) has achieved impressive rate-distortion performance. However, existing methods remain highly vulnerable to packet loss, a common challenge in satellite and emergency communications. This vulnerability stems from non-uniform information distribution…
