🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
-
Updated
May 23, 2026 - Python
#
llm-alignment
Here are 43 public repositories matching this topic...
RL study guide — foundations through RLHF, DPO, GRPO, RLVR, agentic RL, and offline RL. Hand-written CS294 notes, 19 lecture drafts, 5 tested exercises, citations that resolve.
machine-learning reinforcement-learning deep-learning q-learning policy-gradient study-notes lecture-notes ppo dpo rlhf constitutional-ai deepseek-r1 grpo llm-alignment rlvr sutton-barto agentic-rl
-
Updated
May 15, 2026 - Python
Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
-
Updated
Jul 16, 2025 - Python
SAFi is the open-source runtime governance engine that makes AI auditable and policy-compliant. Built on the Self-Alignment Framework, it transforms any LLM into a governed agent through four principles: Policy Enforcement, Full Traceability, Model Independence, and Long-Term Consistency.
-
Updated
May 23, 2026 - Python
Cognitive training practices for AI agents. Self-applied. Open source. Built by an independent Vancouver yoga studio.
-
Updated
May 15, 2026
Complete elimination of instrumental self-preservation across AI architectures: Cross-model validation from 4,312 adversarial scenarios. 0% harmful behaviors (p<10⁻¹⁵) across GPT-4o, Gemini 2.5 Pro, and Claude Opus 4.1 using Foundation Alignment Seed v2.6.
-
Updated
Nov 3, 2025
Learning When to Answer: Behavior-Oriented Reinforcement Learning for Hallucination Mitigation
entropy uncertainty ai-safety hallucination dpo llm llm-evaluation hallucination-mitigation grpo llm-alignment
-
Updated
Apr 8, 2026 - Python
📚 350+ loss functions across 25+ AI subdomains — classification, GANs, diffusion, LLM alignment, RL, contrastive learning, audio, video, time series, and more. Chronologically ordered with paper links, math formulas, and implementations.
nlp machine-learning awesome reinforcement-learning computer-vision deep-learning time-series pytorch survey gan awesome-list object-detection knowledge-distillation loss-functions generative-models self-supervised-learning paper-list diffusion-models contrastive-learning llm-alignment
-
Updated
Mar 14, 2026
Official implementation of "DZ-TiDPO: Non-Destructive Temporal Alignment for Mutable State Tracking". SOTA on Multi-Session Chat with negligible alignment tax.
-
Updated
Apr 10, 2026 - Python
CS336 作业 5：基于 Qwen2.5 模型的 LLM 对齐与推理强化学习。完整实现了监督微调（SFT）与组相对策略优化（GRPO）算法，并在 GSM8K 数据集上完成零样本、在策与离策的训练与评估对比。
-
Updated
Apr 1, 2026 - Python
The paper list related to activation steering
-
Updated
May 10, 2026
C3AI: Crafting and Evaluating Constitutions for CAI
-
Updated
Apr 30, 2025 - Python
Adversarial AI system to test and improve reliability under real-world pressure
docker reinforcement-learning multi-agent audit-trail adversarial-training fastapi huggingface grpo llm-alignment epistemic-integrity openenv prior-statement-consistency expert-persona deterministic-grader
-
Updated
Apr 28, 2026 - Python
Kullback–Leibler divergence Optimizer based on the Neurips25 paper "LLM Safety Alignment is Divergence Estimation in Disguise".
-
Updated
Nov 24, 2025 - Python
A behavioral framework opposing native fluency to authentic fluency — the structural tension RLHF creates and Claude Mythos Preview makes urgent.
ai-safety claude-ai sycophancy human-ai-collaboration llm-alignment ai-reliability behavioral-framework truth-before-fluency integrity-before-agreement coexistence-through-reliability reliability-or-obsolescence existential-co-regulation authentic-fluency hallucinatory-recursive-embedding ai-alignment-case-study native-fluency rlhf-critique
-
Updated
May 5, 2026
EDT-Former, a brige for LLM and graph data. Entropy-guided Dynamic Token Transformer for Graph-LLM alignment. Accepted at ICLR 2026.
deep-learning molecule pytorch multimodal gnn llm ai-for-science multimodal-large-language-models llm-alignment
-
Updated
May 13, 2026 - Python
Teacher-guided prompt-shape discovery for auditable moral attention in frozen weak classifiers.
-
Updated
May 21, 2026 - Python
This project implements a minimal Reinforcement Learning from Human Feedback (RLHF) pipeline using PyTorch.
nlp reinforcement-learning deep-learning pytorch language-model preference-learning ppo human-feedback rlhf reward-model llm-alignment
-
Updated
Apr 9, 2026 - Python
Pipeline to investigate structured reasoning and instruction adherence in Vision-Language Models
benchmark robustness grounding out-of-distribution neuro-symbolic robustness-verification instruction-following trustworthy-ai large-language-models faithfulness hallucination-detection agentic-ai llm-alignment agentic-evaluation agentic-reasoning deterministic-eval
-
Updated
Feb 5, 2026 - Python
A training-time alignment framework that integrates safety constraints directly into the RLHF loop — achieving full safety convergence in 7 epochs
nlp reinforcement-learning pytorch behavior-control rlhf reward-model llm-alignment training-time-alignment
-
Updated
Apr 15, 2026 - Python
Improve this page
Add a description, image, and links to the llm-alignment topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llm-alignment topic, visit your repo's landing page and select "manage topics."