Chinese content双保真采样超网络框架用于材料响应建模与不确定性量化
这篇 arXiv 论文面向做仿真替代模型或工程不确定性量化的人。它把双保真建模和 Langevin 采样超网络结合起来，在实验、仿真和合成数据上验证，比单点拟合能给出后验不确定性，实验数据不够时也能用低保真数据补。
#hypernetworks
9 stories · 1 in 7 days · 2 in 30 days
Stories, products and papers tagged "hypernetworks", newest first.
Nov 10
Oct 19
Chinese contentNestedVLA：用嵌套超网络为 VLA 机器人模型按任务生成技能参数
一篇 VLA 机器人论文，思路是超网络按任务生成参数而不做参数合并，三个基准上最强基线平均高出 41 个百分点，代码也开源了。
Oct 11
Internalizer maps context to parameters for DeepSeek V4-Flash
The shared-expert placement means one hypernetwork can steer every layer's routed experts at once, which sidesteps the usual per-layer adapter sprawl and could make context injection cheaper at inference time. Teams running Mixture-of-Experts models such as DeepSeek V4-Flash or Qwen variants should watch whether the mapping survives fine-tuning and long-context loads before adopting it over LoRA.
Oct 9
Chinese contentInternalizer 超网络可将文档编译为 284B 参数模型的 LoRA 适配器
把一份文档直接编译成 LoRA 权重，284B 的 DeepSeek v4 Flash 也能用，top-1 准确率从 63.4% 拉到 84.9%
Sep 22
Sep 21
Boltzbit and Cambridge propose hypernetwork method to write knowledge into LLM weights
The method targets the pain of re-reading long documents every turn and forgetting after each session, a practical cost issue for anyone building chat assistants on Claude, ChatGPT or open-source models today.
Jun 20
Papers08:51
Chinese contentSakana AI 研究员在 DLCT 期刊俱乐部介绍 Doc-to-LoRASakana AI 介绍了 Doc-to-LoRA，用超网络一键生成 LoRA 权重，微调更省钱。
Jun 5
Chinese contentCode2LoRA：用超网络生成仓库级代码适配器，零推理开销
做代码仓库级上下文注入的团队终于有了一个轻量方案——Code2LoRA 用超网络生成适配器，省去逐仓库微调的成本，还支持代码演化场景。做代码补全或仓库级 AI 工具的开发者值得试试这个零推理开销的思路。