Our survey: AI Alignment: A Contemporary Survey has been accepted by ACM Computing Surveys, Impact Factor: 28.0 (ranked 1/147 in Computer Science Theory & Methods).

Five papers (2*Spotlight, 3*Poster) are accepted by NeurIPS 2025.

Language Model Resist Alignment has been awarded the ACL 2025 Best Paper!

MedAligner has been accepted to The Innovation (Impact Factor=32.1).

Four papers are accepted by ACL 2025 Main.

SAE-V has been accepted as ICML 2025.

Seq2Seq RM (Oral) and StreamAligner have been accepted to AAAI 2025.

Aligner (Oral), ProgressGym (Spotlight) and Safe Sora have been accepted to NeurIPS 2024.

RL framework: OmniSafe is accepted by JMLR 2024 (The most popular Safe Reinforcement Learning framework).

We released PKU-SafeRLHF dataset, the 2nd version of BeaverTails (The total number of downloads: 800K+).

Safe RLHF (Spotlight) and SafeDreamer have been accepted to ICLR 2024.

Big News! We released AI Alignment: A Comprehensive Survey.