Page Index - chunhualiao/public-docs GitHub Wiki
566 page(s) in this GitHub Wiki:
- Home
- AI Software Engineer
- AI scientist
- AI entrepreneurs
- AI politicians
- Generalist agents
- .clineignore
- Please reload this page
- Absolute Zero 2025
- Please reload this page
- absolute zero 2025:building blocks
- Please reload this page
- Actor critic algorithm
- Please reload this page
- adaptive testing
- Please reload this page
- adaptive testing:Gemini 2.5 Pro Experimental
- Please reload this page
- adaptive testing:related work
- Please reload this page
- Adobe reader
- Please reload this page
- agent
- Please reload this page
- agent based system
- Please reload this page
- Agent S
- Please reload this page
- Agent S:example
- Please reload this page
- agentic coding capabilities
- Please reload this page
- agent‐based systems
- Please reload this page
- AI Powered Automation of Research Proposal Writing and Review in STEM
- Please reload this page
- AI scientist
- Please reload this page
- AI software engineer
- Please reload this page
- AI software engineer:challenge
- Please reload this page
- algorithm
- Please reload this page
- AlphaEvolve
- Please reload this page
- arxiv
- Please reload this page
- assert
- Please reload this page
- AutoCodeRover
- Please reload this page
- AutoGen
- Please reload this page
- bellman equation
- Please reload this page
- benchmark
- Please reload this page
- best papers in 2023
- Please reload this page
- best papers in 2024
- Please reload this page
- best papers in 2025
- Please reload this page
- bibtex
- Please reload this page
- biology
- Please reload this page
- Biology of a Large Language Model
- Please reload this page
- blog
- Please reload this page
- BOOST_ASSERT_MSG
- Please reload this page
- car racing
- Please reload this page
- car racing:output
- Please reload this page
- cart pole
- Please reload this page
- cart pole: checkpoint vs. final model files
- Please reload this page
- cart pole:agent
- Please reload this page
- cart pole:neural network
- Please reload this page
- cart pole:simulate
- Please reload this page
- cart pole:state space
- Please reload this page
- cart pole:train
- Please reload this page
- chat with your code
- Please reload this page
- checkpointing and resuming
- Please reload this page
- citation
- Please reload this page
- claude code
- Please reload this page
- Cline
- Please reload this page
- cline and pdf
- Please reload this page
- cline vs windsurf
- Please reload this page
- cline:developer process
- Please reload this page
- cline:file creation and editing
- Please reload this page
- cline:how does it modify source code
- Please reload this page
- cline:internal workflow
- Please reload this page
- cline:large codebase challenge
- Please reload this page
- cline:latex
- Please reload this page
- cline:paper and code repos
- Please reload this page
- cline:proposal
- Please reload this page
- cline:rules
- Please reload this page
- cline:rules:latex paper example 1
- Please reload this page
- cline:workflow
- Please reload this page
- clip function
- Please reload this page
- Code Compliance checking
- Please reload this page
- code generation
- Please reload this page
- code review
- Please reload this page
- Code2Doc
- Please reload this page
- CodeAct
- Please reload this page
- CodeQL
- Please reload this page
- CodeQL vs. Datalog
- Please reload this page
- colliding file names
- Please reload this page
- combination
- Please reload this page
- community
- Please reload this page
- CompilerGPT
- Please reload this page
- computer
- Please reload this page
- conda
- Please reload this page
- conference
- Please reload this page
- context window size
- Please reload this page
- Correctness of large language models
- Please reload this page
- critical thinking
- Please reload this page
- debate
- Please reload this page
- debate:judge
- Please reload this page
- debate:mistakes
- Please reload this page
- debate:universal basic income
- Please reload this page
- deep research
- Please reload this page
- deep search
- Please reload this page
- DeepSeek R1
- Please reload this page
- DeepSeek R1 Zero
- Please reload this page
- DeepSeek R1 Zero:reproducers
- Please reload this page
- DeepSeek R1:Code2Doc
- Please reload this page
- DeepSeek R1:distillation
- Please reload this page
- DeepSeek R1:reward model
- Please reload this page
- DeepSeek‐R1
- Please reload this page
- DeepWiki
- Please reload this page
- DeepWiki Open
- Please reload this page
- diagram
- Please reload this page
- double‐entry bookkeeping
- Please reload this page
- Doxygen
- Please reload this page
- doxygen:config:all func bodies
- Please reload this page
- doxygen:dox
- Please reload this page
- doxygen:multiple comments
- Please reload this page
- doxygen:overloaded function
- Please reload this page
- doxygen:xml
- Please reload this page
- DSPy
- Please reload this page
- embedding model
- Please reload this page
- enjoy
- Please reload this page
- Epsilon greedy policy
- Please reload this page
- fine‐tune models
- Please reload this page
- flyer and poster
- Please reload this page
- Fortran2Cpp
- Please reload this page
- function‐calling LLMs
- Please reload this page
- Funding
- Please reload this page
- GAIA
- Please reload this page
- GAIA benchmark
- Please reload this page
- Gemini 2.0
- Please reload this page
- Gemma 3
- Please reload this page
- git
- Please reload this page
- git repo to single file
- Please reload this page
- GPU
- Please reload this page
- grant
- Please reload this page
- graph
- Please reload this page
- GraphML
- Please reload this page
- GraphML Editors
- Please reload this page
- GraphML vs DOT Graphs
- Please reload this page
- greatest debates
- Please reload this page
- Group Relative Policy Optimization
- Please reload this page
- GRPO
- Please reload this page
- GRPO:Objective Function
- Please reload this page
- Hackathon
- Please reload this page
- hallucination
- Please reload this page
- health insurance
- Please reload this page
- Heritage Foundation
- Please reload this page
- history
- Please reload this page
- humanity
- Please reload this page
- immune system
- Please reload this page
- interpretable proxy model
- Please reload this page
- JSON
- Please reload this page
- KL coefficient
- Please reload this page
- KL divergence
- Please reload this page
- knowledge graph
- Please reload this page
- large language model
- Please reload this page
- leaderboard
- Please reload this page
- leaderboard:programming language translation
- Please reload this page
- legal QA systems
- Please reload this page
- lei2023creating
- Please reload this page
- LEXAM
- Please reload this page
- LlamaIndex
- Please reload this page
- LM‐as‐a‐Judge
- Please reload this page
- long context deep comprehension
- Please reload this page
- machine translation
- Please reload this page
- MacOS
- Please reload this page
- macOS Preview
- Please reload this page
- makefile
- Please reload this page
- mamba
- Please reload this page
- MAP Elites
- Please reload this page
- Markov decision process
- Please reload this page
- math
- Please reload this page
- MCP
- Please reload this page
- MCP server
- Please reload this page
- mermaid rendering
- Please reload this page
- Meta prompting
- Please reload this page
- milestones and deliverables
- Please reload this page
- multi agent framework
- Please reload this page
- Multi objective optimization
- Please reload this page
- OCR
- Please reload this page
- ollama
- Please reload this page
- ollama:streaming mode
- Please reload this page
- on policy vs. off policy learning
- Please reload this page
- open source software for working
- Please reload this page
- Open WebUI
- Please reload this page
- OpenAI o1
- Please reload this page
- OpenAI o3
- Please reload this page
- OpenHands
- Please reload this page
- OpenHands vs Cline
- Please reload this page
- OpenHands:bug fixes
- Please reload this page
- OpenHands:SWE Bench
- Please reload this page
- OpenHands:ubuntu container
- Please reload this page
- OpenRouter
- Please reload this page
- open‐weight models and context window sizes
- Please reload this page
- pain point
- Please reload this page
- paper
- Please reload this page
- PaperBench
- Please reload this page
- paperless ngx
- Please reload this page
- Parquet
- Please reload this page
- Pass@K
- Please reload this page
- Please reload this page
- perlmutter
- Please reload this page
- plot rendering in markdown
- Please reload this page
- political orientation test
- Please reload this page
- powerpoint
- Please reload this page
- PPO
- Please reload this page
- PPO:implementation
- Please reload this page
- problem
- Please reload this page
- program database
- Please reload this page
- programming language translation
- Please reload this page
- prompt
- Please reload this page
- prompt engineering
- Please reload this page
- prompts to elicit innovative ideas
- Please reload this page
- proposal
- Please reload this page
- proposal review
- Please reload this page
- Proximal Policy Optimization
- Please reload this page
- python
- Please reload this page
- python:scope
- Please reload this page
- Q learning algorithm
- Please reload this page
- Q learning algorithm:convergence
- Please reload this page
- Q learning algorithm:episodes and steps
- Please reload this page
- QA of codebases:Gemini 1.5 Pro deep research
- Please reload this page
- QA of codebases:GPT 4o
- Please reload this page
- QA of codebases:Perplexity deep research
- Please reload this page
- question answering of codebases
- Please reload this page
- Q‐table
- Please reload this page
- RAG
- Please reload this page
- Ray
- Please reload this page
- read
- Please reload this page
- reasoning capabilities
- Please reload this page
- reference management
- Please reload this page
- Reflexion
- Please reload this page
- reinforcement learning
- Please reload this page
- reinforcement learning:policy
- Please reload this page
- reinforcement learning:report
- Please reload this page
- reinforcement learning:suitable problems
- Please reload this page
- rejection sampling
- Please reload this page
- related work
- Please reload this page
- related work:ai generation
- Please reload this page
- remove remote branches identical to master
- Please reload this page
- review
- Please reload this page
- RL
- Please reload this page
- RL:projects
- Please reload this page
- rl_gridworld.py
- Please reload this page
- rl_gridworld.py:understanding
- Please reload this page
- rl_llm_gridworld.py
- Please reload this page
- rose:colliding header files
- Please reload this page
- SARSA
- Please reload this page
- search engine
- Please reload this page
- semantic search
- Please reload this page
- seven step problem solving model
- Please reload this page
- silver lining
- Please reload this page
- six thinking hats
- Please reload this page
- SLURM
- Please reload this page
- Slurm job script and srun
- Please reload this page
- softmax
- Please reload this page
- supply chain management
- Please reload this page
- SWE bench
- Please reload this page
- switch‐case
- Please reload this page
- tax software
- Please reload this page
- taxonomy
- Please reload this page
- Technology
- Please reload this page
- technology tree
- Please reload this page
- terminal
- Please reload this page
- Tesla Model Y
- Please reload this page
- text to speech
- Please reload this page
- The Debater’s Guide
- Please reload this page
- They Say I Say
- Please reload this page
- TinyZero
- Please reload this page
- TinyZero:Action
- Please reload this page
- TinyZero:dataset
- Please reload this page
- TinyZero:reward function
- Please reload this page
- TinyZero:training
- Please reload this page
- token
- Please reload this page
- tokens per second
- Please reload this page
- train_tiny_zero.sh
- Please reload this page
- translation
- Please reload this page
- Tulip
- Please reload this page
- unit testing
- Please reload this page
- veRL
- Please reload this page
- veRL:HPC cluster
- Please reload this page
- veRL:trainer main_generation.py
- Please reload this page
- veRL:training
- Please reload this page
- veRL:why bother
- Please reload this page
- verRL:load dataset
- Please reload this page
- verRL:training
- Please reload this page
- vertical bar
- Please reload this page
- vim
- Please reload this page
- war
- Please reload this page
- WebArena
- Please reload this page
- wget
- Please reload this page
- what do I want to do?
- Please reload this page
- why do we have problems
- Please reload this page
- Windsurf
- Please reload this page
- windsurf vs allhands
- Please reload this page
- yEd
- Please reload this page