Humanity's Last Exam
Paper
•
2501.14249
•
Published
•
77
AI & ML interests
AI Safety & AI Security
Recent Activity
View all activity
Papers
X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates
ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks
redteamhacker
authored
2
papers
19 days ago
Eugenie1123
authored
a
paper
19 days ago
redteamhacker
authored
6
papers
19 days ago
ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
Paper
•
2502.04757
•
Published
•
2
When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs
Paper
•
2508.03365
•
Published
•
4
Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models
Paper
•
2508.04196
•
Published
•
1
ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks
Paper
•
2508.16889
•
Published
•
2
X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates
Paper
•
2509.08729
•
Published
•
1
sudo rm -rf agentic_security
Paper
•
2503.20279
•
Published
•
1
Albertmade
authored
a
paper
2 months ago
Dasool
authored
10
papers
3 months ago
Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap
Paper
•
2501.02448
•
Published
Multi-Step Reasoning in Korean and the Emergent Mirage
Paper
•
2501.05712
•
Published
Improving Fine-grained Visual Understanding in VLMs through Text-Only Training
Paper
•
2412.12940
•
Published
KoMultiText: Large-Scale Korean Text Dataset for Classifying Biased Speech in Real-World Online Services
Paper
•
2310.04313
•
Published
HRET: A Self-Evolving LLM Evaluation Toolkit for Korean
Paper
•
2503.22968
•
Published
Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systems
Paper
•
2311.02240
•
Published
Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition
Paper
•
2505.15367
•
Published
•
2
No Language Data Left Behind: A Comparative Study of CJK Language Datasets in the Hugging Face Ecosystem
Paper
•
2507.04329
•
Published
When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs
Paper
•
2508.03365
•
Published
•
4
Ko-PIQA: A Korean Physical Commonsense Reasoning Dataset with Cultural Context
Paper
•
2509.11303
•
Published