6 papers
Decoupled Contrastive Decoding via Expert-Aligned Drafting
Zhixuan Liu, Zhichen Dong, Yuanfu Wang +1
Contrastive Decoding (CD) improves generation quality, but its amateur-model pass makes decoding expensive. Accelerating CD with speculative decoding raises a proposal-alignment qu…
Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
Yuanfu Wang, Zhixuan Liu, Xiangtian Li +2
The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally con…
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
Shanghai AI Lab, :, Yicheng Bao +115
We introduce SafeWork-R1, a cutting-edge multimodal reasoning model that demonstrates the coevolution of capabilities and safety. It is developed by our proposed SafeLadder framewo…
Adversarial Preference Learning for Robust LLM Alignment
Yuanfu Wang, Pengyu Wang, Chenyang Xi +13
Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to th…
Inference-Time Language Model Alignment via Integrated Value Guidance
Zhixuan Liu, Zhanhui Zhou, Yuanfu Wang +2
Large language models are typically fine-tuned to align with human preferences, but tuning large models is computationally intensive and complex. In this work, we introduce $\texti…
Critic-Guided Decision Transformer for Offline Reinforcement Learning
Yuanfu Wang, Chao Yang, Ying Wen +2
Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Return-Conditioned Supervised Learning (RCSL), a paradigm that learns the action dis…