Risultati ricerca autore :: Library Catalog

1

Safety of Embodied Navigation: A Survey Autoría: Wang, Zixia, Hu, Jia, Mu, Ronghui

Pubblicazione 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
2

Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers Autoría: Jin, Gaojie, Huang, Tianjin, Mu, Ronghui, Huang, Xiaowei

Pubblicazione 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
3

ThermoRL:Structure-Aware Reinforcement Learning for Protein Mutation Design to Enhance Thermostability Autoría: Wang, Xiangwen, Jin, Gaojie, Huang, Xiaowei, Mu, Ronghui

Pubblicazione 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
4

CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing Autoría: Wang, Zixia, Jin, Gaojie, Hu, Jia, Mu, Ronghui

Pubblicazione 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
5

Towards Fairness-Aware Adversarial Learning Autoría: Zhang, Yanghao, Zhang, Tianle, Mu, Ronghui, Huang, Xiaowei, Ruan, Wenjie

Pubblicazione 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
6

Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environments Autoría: Jin, Gaojie, Mu, Ronghui, Yi, Xinping, Huang, Xiaowei, Zhang, Lijun

Pubblicazione 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
7

Enhancing Robust Fairness via Confusional Spectral Regularization Autoría: Jin, Gaojie, Wu, Sihao, Liu, Jiaxu, Huang, Tianjin, Mu, Ronghui

Pubblicazione 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
8

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Autoría: Li, Xinyu, Huang, Tianjin, Mu, Ronghui, Huang, Xiaowei, Jin, Gaojie

Pubblicazione 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
9

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents Autoría: Li, Xinyu, Mu, Ronghui, Li, Lin, Huang, Tianjin, Jin, Gaojie

Pubblicazione 2026

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
10

Building Guardrails for Large Language Models Autoría: Dong, Yi, Mu, Ronghui, Jin, Gaojie, Qi, Yi, Hu, Jinwei, Zhao, Xingyu, Meng, Jie, Ruan, Wenjie, Huang, Xiaowei

Pubblicazione 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
11

Safeguarding Large Language Models: A Survey Autoría: Dong, Yi, Mu, Ronghui, Zhang, Yanghao, Sun, Siqi, Zhang, Tianle, Wu, Changshun, Jin, Gaojie, Qi, Yi, Hu, Jinwei, Meng, Jie, Bensalem, Saddek, Huang, Xiaowei

Pubblicazione 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:
12

Confusion-Aware Spectral Regularizer for Long-Tailed Recognition Autoría: Zhu, Ziquan, Jin, Gaojie, Zhu, Hanruo, Lu, Si-Yuan, Zhang, Yunxiao, Fu, Zeyu, Mu, Ronghui, Zhang, Guoqiang, Sun, Zhao, Yuhang, Xia, Shang, Jiaxing, Li, Xiang, Liu, Lu, Huang, Tianjin

Pubblicazione 2026

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Record autonomo
Aggiungi alla lista

Salvato in:

Safety of Embodied Navigation: A Survey Autoría: Wang, Zixia, Hu, Jia, Mu, Ronghui

Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers Autoría: Jin, Gaojie, Huang, Tianjin, Mu, Ronghui, Huang, Xiaowei

ThermoRL:Structure-Aware Reinforcement Learning for Protein Mutation Design to Enhance Thermostability Autoría: Wang, Xiangwen, Jin, Gaojie, Huang, Xiaowei, Mu, Ronghui

CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing Autoría: Wang, Zixia, Jin, Gaojie, Hu, Jia, Mu, Ronghui

Towards Fairness-Aware Adversarial Learning Autoría: Zhang, Yanghao, Zhang, Tianle, Mu, Ronghui, Huang, Xiaowei, Ruan, Wenjie

Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environments Autoría: Jin, Gaojie, Mu, Ronghui, Yi, Xinping, Huang, Xiaowei, Zhang, Lijun

Enhancing Robust Fairness via Confusional Spectral Regularization Autoría: Jin, Gaojie, Wu, Sihao, Liu, Jiaxu, Huang, Tianjin, Mu, Ronghui

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Autoría: Li, Xinyu, Huang, Tianjin, Mu, Ronghui, Huang, Xiaowei, Jin, Gaojie

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents Autoría: Li, Xinyu, Mu, Ronghui, Li, Lin, Huang, Tianjin, Jin, Gaojie

Building Guardrails for Large Language Models Autoría: Dong, Yi, Mu, Ronghui, Jin, Gaojie, Qi, Yi, Hu, Jinwei, Zhao, Xingyu, Meng, Jie, Ruan, Wenjie, Huang, Xiaowei

Safeguarding Large Language Models: A Survey Autoría: Dong, Yi, Mu, Ronghui, Zhang, Yanghao, Sun, Siqi, Zhang, Tianle, Wu, Changshun, Jin, Gaojie, Qi, Yi, Hu, Jinwei, Meng, Jie, Bensalem, Saddek, Huang, Xiaowei

Confusion-Aware Spectral Regularizer for Long-Tailed Recognition Autoría: Zhu, Ziquan, Jin, Gaojie, Zhu, Hanruo, Lu, Si-Yuan, Zhang, Yunxiao, Fu, Zeyu, Mu, Ronghui, Zhang, Guoqiang, Sun, Zhao, Yuhang, Xia, Shang, Jiaxing, Li, Xiang, Liu, Lu, Huang, Tianjin

Risultati della ricerca - Mu, Ronghui

Safety of Embodied Navigation: A Survey Autoría: Wang, Zixia, Hu, Jia, Mu, Ronghui

Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers Autoría: Jin, Gaojie, Huang, Tianjin, Mu, Ronghui, Huang, Xiaowei

ThermoRL:Structure-Aware Reinforcement Learning for Protein Mutation Design to Enhance Thermostability Autoría: Wang, Xiangwen, Jin, Gaojie, Huang, Xiaowei, Mu, Ronghui

CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing Autoría: Wang, Zixia, Jin, Gaojie, Hu, Jia, Mu, Ronghui

Towards Fairness-Aware Adversarial Learning Autoría: Zhang, Yanghao, Zhang, Tianle, Mu, Ronghui, Huang, Xiaowei, Ruan, Wenjie

Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environments Autoría: Jin, Gaojie, Mu, Ronghui, Yi, Xinping, Huang, Xiaowei, Zhang, Lijun

Enhancing Robust Fairness via Confusional Spectral Regularization Autoría: Jin, Gaojie, Wu, Sihao, Liu, Jiaxu, Huang, Tianjin, Mu, Ronghui

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization Autoría: Li, Xinyu, Huang, Tianjin, Mu, Ronghui, Huang, Xiaowei, Jin, Gaojie

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents Autoría: Li, Xinyu, Mu, Ronghui, Li, Lin, Huang, Tianjin, Jin, Gaojie

Building Guardrails for Large Language Models Autoría: Dong, Yi, Mu, Ronghui, Jin, Gaojie, Qi, Yi, Hu, Jinwei, Zhao, Xingyu, Meng, Jie, Ruan, Wenjie, Huang, Xiaowei

Safeguarding Large Language Models: A Survey Autoría: Dong, Yi, Mu, Ronghui, Zhang, Yanghao, Sun, Siqi, Zhang, Tianle, Wu, Changshun, Jin, Gaojie, Qi, Yi, Hu, Jinwei, Meng, Jie, Bensalem, Saddek, Huang, Xiaowei

Confusion-Aware Spectral Regularizer for Long-Tailed Recognition Autoría: Zhu, Ziquan, Jin, Gaojie, Zhu, Hanruo, Lu, Si-Yuan, Zhang, Yunxiao, Fu, Zeyu, Mu, Ronghui, Zhang, Guoqiang, Sun, Zhao, Yuhang, Xia, Shang, Jiaxing, Li, Xiang, Liu, Lu, Huang, Tianjin

Strumenti per la ricerca: