7 papers · 1 filter
Enhance the Safety in Reinforcement Learning by ADRC Lagrangian Methods
Mingxu Zhang, Huicheng Zhang, Jiaming Ji +2
Safe reinforcement learning (Safe RL) seeks to maximize rewards while satisfying safety constraints, typically addressed through Lagrangian-based methods. However, existing approac…
SAE-V: Interpreting Multimodal Models for Enhanced Alignment
Hantao Lou, Changye Li, Jiaming Ji +1
With the integration of image modality, the semantic space of multimodal large language models (MLLMs) is more complex than text-only models, making their interpretability more cha…
Reward Generalization in RLHF: A Topological Perspective
Tianyi Qiu, Fanzhi Zeng, Jiaming Ji +7
Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune langua…
Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
Jiaming Ji, Xinyu Chen, Rui Pan +13
Multimodal large language models (MLLMs) are essential for building general-purpose AI assistants; however, they pose increasing safety risks. How can we ensure safety alignment of…
J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
Chi-Min Chan, Chunpu Xu, Jiaming Ji +7
The current focus of AI research is shifting from emphasizing model training towards enhancing evaluation quality, a transition that is crucial for driving further advancements in…
RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?
Haotian Xu, Xing Wu, Weinong Wang +11
Can scaling transform reasoning? In this work, we explore the untapped potential of scaling Long Chain-of-Thought (Long-CoT) data to 1000k samples, pioneering the development of a…