11 papers
MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves
Zihan Tan, Leixin Sun, Zitong Shi +28
Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost…
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai +2
While multimodal large language models (MLLMs) extend model capabilities beyond text, they also make safety alignment increasingly challenging. Multimodal safety alignment methods…
Do LLMs Know Their Vulnerable Scenarios?
Ziheng Peng, Huiqi Deng, Haoran Jing +5
Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teami…
Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models
Xuankun Rong, Wenke Huang, Bo Du +2
As large language models (LLMs) are increasingly used in decision support, it is important to understand whether their choices under uncertainty exhibit stable and interpretable be…
SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
Xuankun Rong, Wenke Huang, Tingfeng Wang +3
Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new composition…
MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models
Young-Jun Lee, Byung-Kwan Lee, Jianshu Zhang +9
Vision-and-Language Models (VLMs) have shown impressive capabilities on single-turn benchmarks, yet real-world applications often demand more intricate multi-turn dialogues. Existi…
MAPO: Mixed Advantage Policy Optimization
Wenke Huang, Quan Zhang, Yiyang Fang +11
Recent advances in reinforcement learning for foundation models, such as Group Relative Policy Optimization (GRPO), have significantly improved the performance of foundation models…
Never compromise with vulnerabilities: a comprehensive survey on AI governance
Yuchu Jiang, Jian Zhao, Yuchen Yuan +62
The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, t…
Backdoor Cleaning without External Guidance in MLLM Fine-tuning
Xuankun Rong, Wenke Huang, Jian Liang +5
Multimodal Large Language Models (MLLMs) are increasingly deployed in fine-tuning-as-a-service (FTaaS) settings, where user-submitted datasets adapt general-purpose models to downs…
Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model
Wenke Huang, Jian Liang, Xianda Guo +14
Multi-modal Large Language Models (MLLMs) integrate visual and linguistic reasoning to address complex tasks such as image captioning and visual question answering. While MLLMs dem…
A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
Mang Ye, Xuankun Rong, Wenke Huang +3
With the rapid advancement of Large Vision-Language Models (LVLMs), ensuring their safety has emerged as a crucial area of research. This survey provides a comprehensive analysis o…