notes
13 entries · 7 fields · 33,020 words
nothing matches
2026 13 entries
October
September
- vMF Distribution Read a paper on Zero-Shot (Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics) In it, different latent representations are used for RL tasks and RL dynamics Using the dynamics lat…
- Codex Login Issue Resolution Basic Information: System environment: Linux desktop Application: Codex desktop Proxy tool: Clash Verge Port number: 7897 Network prerequisite: The browser can access ChatGPT normally, and IPv6 has be…
June
- MAC network fix: manual DNS causes campus network authentication failure Environment Setup Device: MacBook Air M5 System: macOS Tahoe 26.4.1 Network: NJU campus network (Web Portal authentication, requires student/staff account login) Problem Description After connecting t…
- How do agents manage a research knowledge base? Recently I've spent quite a bit of time figuring out how to get AI agents to help me read papers more effectively. The process went through roughly three stages, each one fixing the problems of the pr…
- Retargeting Revolution: Why Motion Retargeting Is Becoming the Key to Humanoid Robot Intelligence Subtitle : How four paradigm-shifting papers are redefining the bridge from human motion to robot behavior Abstract For a long time, motion retargeting—the process of mapping human motion capture data…
May
- Mac Development Toolchain Configuration Notes Recently I set up a complete development toolchain on my Mac from scratch — from terminal emulator to editor, from dotfiles management to shell theming — and it took about a weekend of tinkering. Befo…
- UV Getting Started Notes Why I Started Using uv Some open-source projects I've recently been involved with have started using uv as their package manager, and there's a next to every . I'd always used conda to manage Python e…
- From Dayan's Successor Representation to BFM for Humanoid Robots: Decoupling Environment Dynamics and Task Reward Abstract In 1993, Peter Dayan wrote in a paper: Representation is the key—view a problem in the right way and it becomes easy. The right way he proposed was this: represent a state not by what it look…
- Application of Force-Estimation-Based Hybrid Force-Position Control in Humanoid Robots Sixteen papers, five technical routes, one universal equation Abstract : When humanoid robots are deployed in human environments such as homes, hospitals, and offices, they face a common control chall…
March
- Build a personal blog with Hexo + Fluid and host it on GitHub Pages 1. Environment Setup Install the following tools in advance: Node.js (v16+ recommended): refer to the Runoob tutorial for installation]( https://www.runoob.com/nodejs/nodejs-install-setup.html ) Git :…
- Blog About the Blog Why I decided to organize a blog : Since before (roughly starting from my freshman year), I got into the habit of using electronic notes to record all sorts of things. At first I kept t…
- RL Personal Learning Path A reference learning path for reinforcement learning (oriented toward using RL to solve robot control problems) Prerequisites recommended before starting: Linear algebra fundamentals Calculus fundamen…