Representation Engineering: A Top-Down Approach to AI Transparency
Paper
•
2310.01405
•
Published
•
5
Scale AI
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
ScaleAI's activity
ZifanScale
authored
7
papers
2 months ago
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
Paper
•
1910.01279
•
Published
Can LLMs Follow Simple Rules?
Paper
•
2311.04235
•
Published
•
10
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Paper
•
2402.04249
•
Published
•
4
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Paper
•
2403.03218
•
Published
•
1
LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
Paper
•
2408.15221
•
Published
Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents
Paper
•
2410.13886
•
Published
ZifanScale
updated
a
dataset
2 months ago
hendryx-scale
authored
a
paper
2 months ago
mohit-raghavendra
authored
a
paper
2 months ago
hendryx-scale
authored
6
papers
2 months ago
A Careful Examination of Large Language Model Performance on Grade School Arithmetic
Paper
•
2405.00332
•
Published
•
30
Planning In Natural Language Improves LLM Search For Code Generation
Paper
•
2409.03733
•
Published
Learning Goal-Conditioned Representations for Language Reward Models
Paper
•
2407.13887
•
Published
A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shift
Paper
•
2311.14743
•
Published
Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning
Paper
•
2109.00150
•
Published
Meta-Learning Initializations for Image Segmentation
Paper
•
1912.06290
•
Published
mohit-raghavendra
authored
a
paper
2 months ago
hendryx-scale
authored
2
papers
2 months ago
ZifanScale
updated
a
dataset
3 months ago