76 citations · 107 across the 19 of their papers we have counts for
10 papers · 1 filter
MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
Tianzhuo Yang, Zihan Shen, Zirui Mi +7
Action-conditioned world models are increasingly used as scalable simulators for robot learning, yet current evaluations provide limited evidence that their predictions are reliabl…
FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
Jiayi Zhou, Yang Sheng, Hantao Lou +2
As LLM-based agents increasingly operate in high-stakes domains with real-world consequences, ensuring their behavioral safety becomes paramount. The dominant oversight paradigm, L…
Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
Sitong Fang, Shiyi Hou, Kaile Wang +6
Are frontier AI systems becoming more capable? Certainly. Yet such progress is not an unalloyed blessing but rather a Trojan horse: behind their performance leaps lie more insidiou…
Mitigating Deceptive Alignment via Self-Monitoring
Jiaming Ji, Wenqi Chen, Kaile Wang +8
Modern large language models rely on chain-of-thought (CoT) reasoning to achieve impressive performance, yet the same mechanism can amplify deceptive alignment, situations in which…
Generative RLHF-V: Learning Principles from Multi-modal Human Preference
Jiayi Zhou, Jiaming Ji, Boyuan Chen +6
Training multi-modal large language models (MLLMs) that align with human intentions is a long-term challenge. Traditional score-only reward models for alignment suffer from low acc…
InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
Boyuan Chen, Donghai Hong, Jiaming Ji +12
As multimodal large models (MLLMs) continue to advance across challenging tasks, a key question emerges: What essential capabilities are still missing? A critical aspect of human l…
Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback
Jiaming Ji, Jiayi Zhou, Hantao Lou +16
Reinforcement learning from human feedback (RLHF) has proven effective in enhancing the instruction-following capabilities of large language models; however, it remains underexplor…
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
Jiaming Ji, Donghai Hong, Borong Zhang +10
In this study, we introduce the safety human preference dataset, PKU-SafeRLHF, designed to promote research on safety alignment in large language models (LLMs). As a sibling projec…
AI Alignment: A Comprehensive Survey
Jiaming Ji, Tianyi Qiu, Boyuan Chen +23
AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and…
Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
Jiaming Ji, Borong Zhang, Jiayi Zhou +7
Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. S…