PGrad: Learning Principal Gradients For Domain Generalization
Paper
•
2305.01134
•
Published
•
1
QJ
DrQdata
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
AIDE: Task-Specific Fine Tuning with Attribute Guided Multi-Hop Data
Expansion
upvoted
a
paper
6 days ago
PGrad: Learning Principal Gradients For Domain Generalization
Organizations
upvoted
5
papers
6 days ago
TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
Paper
•
2502.18504
•
Published
•
1
A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning
Paper
•
2503.12339
•
Published
•
1
Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency
Paper
•
2508.14314
•
Published
•
1
Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation
Paper
•
2501.18638
•
Published
•
1