The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
-
Updated
Nov 12, 2026 - Python
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
preferenceHere are 69 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
training machine-learning reinforcement-learning deep-learning deep-reinforcement-learning distributed artificial-intelligence multi-agent hyperparameter-optimization agents preference hpo reasoning post-training sft rft llm agilerl open-weight
A highly customizable color picker for Android
Selecting directories/files made a lot easier.
💐 An easy way to persist and run code block only as many times as necessary on Android.
[AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
[ICLR 2025] LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation
moe preference knowledge-distillation distillation kd hallucination mixture-of-experts large-language-models llm rlhf mllm llava multimodal-large-language-models qwen
💾 A Powerful library to control and simplify the usage of shared preference in Android.
android debugging preferences database sharedpreferences sqlite android-library android-development debug android-debug-database shared-preferences preference storage-android sharedpreferences-editor sharedpreferences-manager shared-preferences-manager room-persistence-library sharedpreference-viewer room-database
The coolest and easiest way to manage your user's preferences on the client side with your preferred storage. Check out sample app here:
How HTML, CSS, and JavaScript support dark mode for iOS and macOS.
[NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages
Speech (audio) subjective evaluation system
The Stable Matching or the Stable Marriage algorithm is a mathematical algorithm that finds stable matches between two equally sized sets of elements, the proposers and the acceptors. This project uses basic Python data structures to implement the algorithm.
For accessing to the dataset, please send your short bio and objective of the study to Dr.Theerawit Wilaiprasitporn (theerawit dot w at vistec dot ac dot th)
A tiny pin to reduce boilerplate Preference codes in Android.
Lib-Preferences is a library for easy storing simple data to a Preferences.properties file in a Java(FX) & Maven desktop application.
java preferences library netbeans maven javafx file java-8 java-library javafx-library preference javafx-8
Add this topic to your repoTo associate your repository with the preference topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |