All Posts

$\pi_{0.5}$代码解读
π0.5\pi_{0.5}代码解读
发表于|vla|vla
从数据流的角度看$\pi_{0.5}$的完整架构和流程
Sigmoid Loss for Language Image Pre-Training.md
Sigmoid Loss for Language Image Pre-Training.md
发表于|vlm|vlm
关于ViT和SigLiP的博客
gello遥操作.md
发表于|vla|vla
gello的遥操映射代码解读
Decentralized Asynchronous Multi-player Bandits
Decentralized Asynchronous Multi-player Bandits
发表于|paperbandit|bandit•distributed
ACE algorithm
What Makes a Good Prune Maximal Unstructured Pruning for Maximal Cosine Similarity
What Makes a Good Prune Maximal Unstructured Pruning for Maximal Cosine Similarity
发表于|paperllm|prune•llm•visualization
We develop the idea that cosine similarity is an effective proxy measure for functional similarity between the parent and the pruned network. We show that the higher the kurtosis of a model's parameter distribution, the more it can be pruned while maintaining performance.
SIC-MMAB - Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits
SIC-MMAB - Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits
发表于|paperbandit|bandit•distributed
use collision to transmit information and develop SIC-MMAB algorithm
Distributed Algorithms for Multi-Agent Multi-Armed Bandits with Collision
Distributed Algorithms for Multi-Agent Multi-Armed Bandits with Collision
发表于|paperbandit|bandit•distributed
use collision to transmit information and develop SynC algorithm
STUN - Structured-Then-Unstructured Pruning for Scalable MoE Pruning
STUN - Structured-Then-Unstructured Pruning for Scalable MoE Pruning
发表于|paperllm|prune•llm•MoE
2025年ACL, 一个适用于MoE模型架构的非结构化和结构化的框架, 其中结构化剪枝专家后对每个专家进行非结构化剪枝.
SparseGPT - Massive Language Models Can Be Accurately Pruned in One-Shot
SparseGPT - Massive Language Models Can Be Accurately Pruned in One-Shot
发表于|paperllm|prune•llm•MoE
经典的非结构化剪枝方法Sparsegpt文献阅读与解析
Stochastic bandits robust to adversarial corruptions
Stochastic bandits robust to adversarial corruptions
发表于|paperbandit|bandit•stochastic
使用多层感知的方法来消除污染导致的估计不准确问题
MoE大模型剪枝以及量化
MoE大模型剪枝以及量化
发表于|llm|llm_infra
更精细的,关于MoE大模型的剪枝和量化方法的调研
llm 基础知识
llm 基础知识
发表于|llm|llm
关于大模型的基础知识调研和学习,其中包括多种注意力机制的了解,以及MoE架构,LoRA微调,KV cache
llm infra调研与学习
llm infra调研与学习
发表于|llm|llm_infra
关于大模型的大模型推理加速的调研和学习
Kai Research Gemini-3.1-pro Prompt
Kai Research Gemini-3.1-pro Prompt
发表于|沉思|prompt_engineering
个人开发的一个为计算机学生量身打造的阅读论文prompt🤔, hhh
构想的游戏-k小镇
发表于|沉思|game
ai控制一整个小镇?🤔
修复ubuntu网络断开
发表于|ubuntu
问题描述 在ubuntu的终端输入命令ifconfig弹出127.0.0.1而没有虚拟机的ip地址, 如下图所示 解决方案 在终端输入sudo dhclient -v此时再输入ifcon...
hello-world
发表于
Welcome to Hexo! This is your very first post. Check documentation for more info. If you get any ...