Tag
该论文研究如何通过联合训练策略，让预训练语言模型同时支持单次前向和循环推理两种路径，在保留单次推理质量的同时获得循环计算带来的性能增益。
We introduce TWIG (Tree-structured Weights with Inherited Gates), a representation where every neural network weight is the endpoint of a path of shared discrete decisions, unifying pruning, quantization, low-rank factorization, and weight sharing into a single editable object optimizable via higher-order Boltzmann machine ground-state solvers, achieving 9–15% fewer additions than GPTQ at equal LLM layer error.
A blog post by Günter Klambauer providing an illustrated overview of recurrence in neural networks, tracing its history from Amari-Hopfield Nets to mentions of GPT-6 Astra and categorizing various architectures based on recurrence patterns.
RF-DETR introduces a lightweight detection transformer that uses weight-sharing neural architecture search to achieve state-of-the-art real-time object detection, outperforming prior methods on COCO and Roboflow100-VL while running up to 20x faster.