02 / BLOG02 / 技术文章
Technical Notes技术笔记
Concepts, methods, derivations, and implementation notes.核心概念、技术方法、公式推导与工程笔记。
Writing & working notes文章归档与工作笔记
6 ENTRIES篇Track: 主题分类: Clear track ↗清除分类 ↗
两万字学习 π0.7:从多模态输入到实时动作生成
结合推理时间线与训练前向数据流,拆解 π0.7 如何将多视角图像、视觉子目标、文本提示与本体感知编码为连续与离散联合动作控制。
Neural Networks Are Already Clean
The cause of polysemanticity in early model organisms wasn’t superposition, but several ordinary, mostly fixable issues. A working hypothesis from Goodfire on neurons, generalization, and circuits.
VLA 真的通用吗?—— 机器人具身策略的泛化性与记忆
结合斯坦福 MSL 实验室 Mac Schwager 团队多项实证研究,剖析当前 VLA 与扩散策略的“锁定效应”、动作片段查表记忆化、稀疏自编码器诊断与元认知破局路径。
Constructive Self-Supervised Learning (Part 1): Designing Generalisable Deep Self-Supervision
Designing generalisable deep self-supervision by predicting across an abstraction hierarchy rather than dispersing lower-level details—introducing cI-JEPA (+6.02% linear-probe top-1 over I-JEPA on ImageNet-100).
VLA 架构解析:告别“黑箱”与“空谈”,探寻自动驾驶的“大脑”进化史
从 VA 端到端黑箱、快慢双核 VLM+VA 过渡形态到全可微 VLA 统一大脑,系统拆解视觉(SigLIP+DINOv2 / 3DGS)、语言(LLaMA / MindGPT)、动作解码(Diffusion Transformer)与四阶段演进路线。
Thinking About a Bias for Better Semantic Coherence and Reuse
Why current generative next-token prediction and subtractive latent SSL struggle to bias neural networks toward unified, reusable semantic invariances across levels of abstraction.
No writing matches this filter yet.暂无符合筛选条件的文章。





