papers

Publications (56)

cs.CL2025

SafeMT: Multi-turn Safety for Multimodal Language Models

Han Zhu, Juntao Dai, Jiaming Ji +8

With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interacti…

cs.LG2025

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…

cs.AI2026

ShuttleEnv: An Interactive Data-Driven RL Environment for Badminton Strategy Modeling

Ang Li, Xinyang Gong, Bozhou Chen +5

We present ShuttleEnv, an interactive and data-driven simulation environment for badminton, designed to support reinforcement learning and strategic behavior analysis in fast-paced…

cs.AI2026

VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment

Jiawei Chen, Tianzhuo Yang, Guoxi Zhang +3

Aligning Large Language Models (LLMs) with nuanced human values remains a critical challenge, as existing methods like Reinforcement Learning from Human Feedback (RLHF) often handl…

cs.LG2024

ProgressGym: Alignment with a Millennium of Moral Progress

Tianyi Qiu, Yang Zhang, Xuchuan Huang +3

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values…

cs.CL2025

Baichuan 2: Open Large-scale Language Models

Aiyuan Yang, Bin Xiao, Bingning Wang +52

Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing…

cs.AI2026

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…

cs.CL2026

SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence

Yuyan Bu, Haowei Li, Qirui Zheng +7

As LLM-based agents expand their operational scope, reliability becomes a prerequisite for real-world deployment. However, in practical applications, human users cannot monitor eve…

cs.CL2025

A Survey of LLM-based Agents in Medicine: How far are we from Baymax?

Wenxuan Wang, Zizhan Ma, Zheng Wang +5

Large Language Models (LLMs) are transforming healthcare through the development of LLM-based agents that can understand, reason about, and assist with medical tasks. This survey p…

cs.CL2025

SafeLawBench: Towards Safe Alignment of Large Language Models

Chuxue Cao, Han Zhu, Jiaming Ji +7

With the growing prevalence of large language models (LLMs), the safety of LLMs has raised significant concerns. However, there is still a lack of definitive standards for evaluati…

cs.AI2026

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning

Lichao Wang, Zhaoxing Ren, Tianzhuo Yang +4

As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents u…

cs.RO2026

RedVLA: Physical Red Teaming for Vision-Language-Action Models

Yuhao Zhang, Borong Zhang, Jiaming Fan +4

The real-world deployment of Vision-Language-Action (VLA) models remains limited by the risk of unpredictable and irreversible physical harm. However, we currently lack effective m…

cs.AI2025

A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs

Guoxi Zhang, Jiawei Chen, Tianzhuo Yang +3

The increasing prevalence of large language models (LLMs) is influencing global value systems. However, these models frequently exhibit a pronounced WEIRD (Western, Educated, Indus…

cs.LG2025

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…

cs.LG2025

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…

cs.CL2025

Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback

Jiayi Zhou, Jiaming Ji, Juntao Dai +2

Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs b…

cs.CL2025

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

Shi Qiu, Shaoyang Guo, Zhuo-Yang Song +51

Current benchmarks for evaluating the reasoning capabilities of Large Language Models (LLMs) face significant limitations: task oversimplification, data contamination, and flawed e…

cs.AI2024

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…

cs.LG2026

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…

cs.CV2026

What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning

Yujin Zhou, Pengcheng Wen, Jiale Chen +6

The rapid advancement of Large Vision Language Models (LVLMs) has demonstrated excellent abilities in various visual tasks. Building upon these developments, the thinking with imag…

cs.AI2026

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…

cs.CL2025

Benchmarking Multi-National Value Alignment for Large Language Models

Weijie Shi, Chengyi Ju, Chengzhong Liu +8

Do Large Language Models (LLMs) hold positions that conflict with your country's values? Occasionally they do! However, existing works primarily focus on ethical reviews, failing t…

cs.AI2026

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Dongrui Liu, Qihan Ren, Chen Qian +40

The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk…

cs.AI2025

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…

cs.CL2025

Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications

Wenxuan Wang, Zizhan Ma, Meidan Ding +8

The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, a…

cs.CR2025

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

Kun Wang, Guibin Zhang, Zhenhong Zhou +100

The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communi…

cs.CL2024

Aligner: Efficient Alignment by Learning to Correct

Jiaming Ji, Boyuan Chen, Hantao Lou +6

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 critica…

cs.CV2026

RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations

Jianing Guo, Zhenhong Wu, Chang Tu +13

In Vision-Language-Actionf(VLA) models, robustness to real-world perturbations is critical for deployment. Existing methods target simple visual disturbances, overlooking the broad…

q-bio.QM2026

A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models

Shu Quan, Tianfang Hao, Sitong Fang +8

Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in protein engineering can equal…

cs.AI2023

Safe RLHF: Safe Reinforcement Learning from Human Feedback

Josef Dai, Xuehai Pan, Ruiyang Sun +5

With the development of large language models (LLMs), striking a balance between the performance and safety of AI systems has never been more critical. However, the inherent tensio…

cs.LG2025

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…

cs.LG2022

Constrained Update Projection Approach to Safe Policy Optimization

Long Yang, Jiaming Ji, Juntao Dai +5

Safe reinforcement learning (RL) studies problems where an intelligent agent has to not only maximize reward but also avoid exploring unsafe areas. In this study, we propose CUP, a…

cs.CV2024

SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset

Josef Dai, Tianle Chen, Xuyao Wang +4

To mitigate the risk of harmful outputs from large vision models (LVMs), we introduce the SafeSora dataset to promote research on aligning text-to-video generation with human value…

cs.LG2023

Heterogeneous-Agent Reinforcement Learning

Yifan Zhong, Jakub Grudzien Kuba, Xidong Feng +3

The necessity for cooperation among intelligent machines has popularised cooperative multi-agent reinforcement learning (MARL) in AI research. However, many research endeavours hea…

cs.LG2022

CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning

Long Yang, Jiaming Ji, Juntao Dai +3

Safe reinforcement learning (RL) is still very challenging since it requires the agent to consider both return maximization and safe exploration. In this paper, we propose CUP, a C…

cs.CL2025

Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction

Hantao Lou, Jiaming Ji, Kaile Wang +1

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 human val…

cs.AI2025

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…

cs.AI2025

LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning

Weijie Shi, Han Zhu, Jiaming Ji +7

Legal judgment prediction (LJP) aims to function as a judge by making final rulings based on case claims and facts, which plays a vital role in the judicial domain for supporting c…

cs.CL2025

FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation

Junyu Luo, Zhizhuo Kou, Liming Yang +10

Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years. However, in the financial domain, there is a notable lack of effective and specialized…

cs.LG2024

SafeDreamer: Safe Reinforcement Learning with World Models

Weidong Huang, Jiaming Ji, Chunhe Xia +2

The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) met…

cs.AI2026

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments

Zhiheng Xi, Dingwen Yang, Jiaqi Liu +21

Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic eval…

cs.RO2025

Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning

Minghe Gao, Juncheng Li, Yuze Lin +15

We contend that embodied learning is fundamentally a lifecycle problem rather than a single-stage optimization. Systems that optimize only one link (data collection, simulation, le…

cs.RO2026

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

Borong Zhang, Yuhao Zhang, Jiaming Ji +5

Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-world deployment, including the r…

cs.AI2025

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…

cs.CL2023

BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset

Jiaming Ji, Mickel Liu, Juntao Dai +6

In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety alignment in large language models (LLMs). This dataset uniquely separates annotations of…

cs.AI2026

When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning

Sitong Fang, Wenjing Cao, Jiahao Li +7

Reasoning models have attracted increasing attention for their ability to tackle complex tasks, embodying the System II (slow thinking) paradigm in contrast to System I (fast, intu…

cs.AI2025

Are Your Agents Upward Deceivers?

Dadi Guo, Qingyu Liu, Dongrui Liu +13

Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in…

cs.AI2025

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…

cs.AI2024

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…

cs.AI2025

AI Deception: Risks, Dynamics, and Controls

Boyuan Chen, Sitong Fang, Jiaming Ji +56

As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved from a speculative concern to an…

cs.LG2025

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…

cs.LG2023

OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research

Jiaming Ji, Jiayi Zhou, Borong Zhang +7

AI systems empowered by reinforcement learning (RL) algorithms harbor the immense potential to catalyze societal advancement, yet their deployment is often impeded by significant s…

cs.CL2026

ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs

Pengcheng Wen, Jiaming Ji, Chi-Min Chan +5

Large language models (LLMs) have demonstrated enhanced performance through the \textit{Thinking then Responding} paradigm, where models generate internal thoughts before final res…

cs.RO2026

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models

Borong Zhang, Jiahao Li, Jiachen Shen +7

While Vision-Language-Action models (VLAs) are rapidly advancing towards generalist robot policies, it remains difficult to quantitatively understand their limits and failure modes…

cs.CL2025

Language Models Resist Alignment: Evidence From Data Compression

Jiaming Ji, Kaile Wang, Tianyi Qiu +7

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, so…

cs.AI2025

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…