MoE训练新方案：Sinkhorn梯度下降替代AdamW，减少优化器状态内存，让大模型训练更省显存。
arXiv:2608.04407v1 Announce Type: cross Abstract: Memory-efficient matrix optimizers such as Sinkhorn gradient descent remove most AdamW optimizer sta…
提出 Mediator 框架，通过减少参数冲突和不确定性路由，实现内存高效的 LLM 合并。
arXiv:2502.04411v3 Announce Type: replace-cross Abstract: Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a st…
从数据、内存、计算三方面统一梳理LLM训练效率优化策略，系统总结前沿方法
arXiv:2606.10706v1 Announce Type: cross Abstract: Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large l…
ICML2026接收：动态稀疏性突破LLM训练内存瓶颈，兼顾稳定性与实用规模化
arXiv:2606.00888v1 Announce Type: new Abstract: Dynamic Sparse Training (DST) offers a promising paradigm for improving the training and inference eff…