Copertina

AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pan, Zhenyu, Zhang, Yiting, Liu, Zhuo, Tang, Yolo Yunlong, Zhang, Zeliang, Luo, Haozheng, Han, Yuwei, Zhang, Jianshu, Wu, Dennis, Chen, Hong-Yu, Lu, Haoran, Fang, Haoyang, Li, Manling, Xu, Chenliang, Yu, Philip S., Liu, Han
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety
di: Pan, Zhenyu, et al.
Pubblicazione: (2025)

FairReason: Balancing Reasoning and Social Bias in MLLMs
di: Pan, Zhenyu, et al.
Pubblicazione: (2025)

Conv-CoA: Improving Open-domain Question Answering in Large Language Models via Conversational Chain-of-Action
di: Pan, Zhenyu, et al.
Pubblicazione: (2024)

Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models
di: Pan, Zhenyu, et al.
Pubblicazione: (2024)

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
di: Tan, Zhangyun, et al.
Pubblicazione: (2026)

Learning to Transform Dynamically for Better Adversarial Transferability
di: Zhu, Rongyi, et al.
Pubblicazione: (2024)

CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion
di: Tang, Yolo Yunlong, et al.
Pubblicazione: (2024)

Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
di: Zhang, Zeliang, et al.
Pubblicazione: (2024)

Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability
di: Liu, Jiani, et al.
Pubblicazione: (2025)

Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?
di: Feng, Mingqian, et al.
Pubblicazione: (2024)

V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning
di: Hua, Hang, et al.
Pubblicazione: (2024)

Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
di: Zhang, Zeliang, et al.
Pubblicazione: (2025)

Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?
di: Liang, Susan, et al.
Pubblicazione: (2026)

Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training
di: Zhang, Zeliang, et al.
Pubblicazione: (2024)

Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding
di: Tang, Yolo Yunlong, et al.
Pubblicazione: (2024)

Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
di: Zhang, Zeliang, et al.
Pubblicazione: (2024)

Why Instruction-Based Unlearning Fails in Diffusion Models?
di: Zhang, Zeliang, et al.
Pubblicazione: (2026)

GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
di: Luo, Haozheng, et al.
Pubblicazione: (2025)

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
di: Zhang, Zeliang, et al.
Pubblicazione: (2024)

Understanding Model Ensemble in Transferable Adversarial Attack
di: Yao, Wei, et al.
Pubblicazione: (2024)

Targeted Forgetting of Image Subgroups in CLIP Models
di: Zhang, Zeliang, et al.
Pubblicazione: (2025)

LaunchpadGPT: Language Model as Music Visualization Designer on Launchpad
di: Xu, Siting, et al.
Pubblicazione: (2023)

Bag of Tricks to Boost Adversarial Transferability
di: Zhang, Zeliang, et al.
Pubblicazione: (2024)

Topology Enhanced MARL for Multi-Vehicle Cooperative Decision-Making of CAVs
di: Han, Ye, et al.
Pubblicazione: (2025)

Training Large Reasoning Models Efficiently via Progressive Thought Encoding
di: Zhang, Zeliang, et al.
Pubblicazione: (2026)

Smart Interrupted Routing Based on Multi-head Attention Mask Mechanism-Driven MARL in Software-defined UASNs
di: Wang, Zhenyu, et al.
Pubblicazione: (2025)

LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning
di: Tang, Yolo Yunlong, et al.
Pubblicazione: (2023)

Forward Learning with Differential Privacy
di: Feng, Mingqian, et al.
Pubblicazione: (2025)

Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?
di: Zhang, Zeliang, et al.
Pubblicazione: (2024)

EvoDR: Evolving Dispatching Rules via Large Language Model for Dynamic Flexible Assembly Flow Shop Scheduling
di: Qiu, Junhao, et al.
Pubblicazione: (2026)

EvoNash-MARL: A Closed-Loop Multi-Agent Reinforcement Learning Framework for Medium-Horizon Equity Allocation
di: Jia, Chongliu, et al.
Pubblicazione: (2026)

EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries
di: Sun, Jing Han, et al.
Pubblicazione: (2024)

EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution
di: Hu, Haichuan, et al.
Pubblicazione: (2026)

Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion
di: Lu, Haoran, et al.
Pubblicazione: (2026)

PROGRESSLM: Towards Progress Reasoning in Vision-Language Models
di: Zhang, Jianshu, et al.
Pubblicazione: (2026)

SPACENUM: Revisiting Spatial Numerical Understanding in VLMs
di: Zhang, Jianshu, et al.
Pubblicazione: (2026)

TDMM-LM: Bridging Facial Understanding and Animation via Language Models
di: Song, Luchuan, et al.
Pubblicazione: (2026)

Does a Global Perspective Help Prune Sparse MoEs Elegantly?
di: Zhang, Zeliang, et al.
Pubblicazione: (2026)

VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
di: Tang, Yolo Y., et al.
Pubblicazione: (2024)

3D printing single‐stroke path planning, local reinforcement and performance testing of MBB beams and cantilever beams
di: Jianshu Wang, et al.
Pubblicazione: (2024)