Picture for Jing Jiang

Jing Jiang

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

Add code
Jun 03, 2024
Viaarxiv icon

Multi-Level Additive Modeling for Structured Non-IID Federated Learning

Add code
May 26, 2024
Viaarxiv icon

Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models

Add code
May 24, 2024
Viaarxiv icon

Speaker Verification in Agent-Generated Conversations

May 16, 2024
Viaarxiv icon

What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning

Add code
Apr 16, 2024
Viaarxiv icon

Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments

Apr 02, 2024
Figure 1 for Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments
Figure 2 for Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments
Figure 3 for Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments
Figure 4 for Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments
Viaarxiv icon

Dual-Personalizing Adapter for Federated Foundation Models

Mar 28, 2024
Figure 1 for Dual-Personalizing Adapter for Federated Foundation Models
Figure 2 for Dual-Personalizing Adapter for Federated Foundation Models
Figure 3 for Dual-Personalizing Adapter for Federated Foundation Models
Figure 4 for Dual-Personalizing Adapter for Federated Foundation Models
Viaarxiv icon

Modularized Networks for Few-shot Hateful Meme Detection

Add code
Feb 19, 2024
Viaarxiv icon

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Add code
Feb 13, 2024
Viaarxiv icon

Knowledge Generation for Zero-shot Knowledge-based VQA

Add code
Feb 04, 2024
Viaarxiv icon