alignment topic

Deploy once. Continuously improve your AI agents in production.

pegasi-ai

Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts

YuejiangLIU

Realign is a testing and simulation framework for AI applications.

honeyhiveai

[ICLR 2025] General-purpose activation steering library

IBM

Wavefront alignment algorithm (WFA) in Golang

shenwei356

WFGY 2.0. Semantic Reasoning Engine for LLMs (MIT). Fixes RAG/OCR drift, collapse & “ghost matches” via symbolic overlays + logic patches. Autoboot; OneLine & Flagship. ⭐ Star if you explore semantic...

onestardao

A Survey of Direct Preference Optimization (DPO)

liushunyu

超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1

sylvain-wei

[AAAI'26 Oral] Official Implementation of STAR-1: Safer Alignment of Reasoning LLMs with 1K Data

UCSC-VLAA

We introduce the direct document relevance optimization (DDRO) for training a pairwise ranker model. DDRO encourages the model to focus on document-level relevance during generation

kidist-amde