Aligner: Efficient alignment by learning to correct

J Ji, B Chen, H Lou, D Hong, B Zhang… - Advances in …, 2025 - proceedings.neurips.cc
With the rapid development of large language models (LLMs) and ever-evolving practical
requirements, finding an efficient and effective alignment method has never been more …

From System 1 to System 2: A Survey of Reasoning Large Language Models

ZZ Li, D Zhang, ML Zhang, J Zhang, Z Liu… - arxiv preprint arxiv …, 2025 - arxiv.org
Achieving human-level intelligence requires refining the transition from the fast, intuitive
System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in …

Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction

H Lou, J Ji, K Wang, Y Yang - arxiv preprint arxiv:2501.05336, 2025 - arxiv.org
The rapid advancement of large language models (LLMs) has led to significant
improvements in their capabilities, but also to increased concerns about their alignment with …

SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings

W Lu, H Peng, H Zhuang, C Chen, Z Zeng - arxiv preprint arxiv …, 2025 - arxiv.org
Multimodal Large Language Models (MLLMs) have serious security vulnerabilities. While
safety alignment using multimodal datasets consisting of text and data of additional …