Nicholas Crispino

ncrispino's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 8 days ago

WangResearchLab/AgentInstruct

Viewer • Updated 8 days ago • 53 • 159 • 2

upvoted 2 papers 10 days ago

Budget-aware Test-time Scaling via Discriminative Verification

Paper • 2510.14913 • Published 12 days ago • 4

Predicting Task Performance with Context-aware Scaling Laws

Paper • 2510.14919 • Published 12 days ago • 3

updated a dataset 12 days ago

WangResearchLab/SteeringSafety

Viewer • Updated 12 days ago • 71.6k • 370 • 2

authored a paper about 1 month ago

RepIt: Representing Isolated Targets to Steer Language Models

Paper • 2509.13281 • Published Sep 16 • 4

updated a collection about 1 month ago

LLM Interpretability

Collection

Interpretability papers from Prof. Chenguang Wang's lab at UCSC • 3 items • Updated Sep 19

upvoted a paper about 1 month ago

COSMIC: Generalized Refusal Direction Identification in LLM Activations

Paper • 2506.00085 • Published May 30 • 2

New activity in WangResearchLab/SteeringSafety about 1 month ago

Add license, task categories, language, tags, and detailed sample usage

1

#2 opened about 1 month ago by

nielsr

upvoted a paper about 1 month ago

RepIt: Representing Isolated Targets to Steer Language Models

Paper • 2509.13281 • Published Sep 16 • 4

authored a paper about 1 month ago

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

Paper • 2509.13450 • Published Sep 16 • 7

commented a paper about 1 month ago

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

Paper • 2509.13450 • Published Sep 16 • 7 •

2

liked a dataset about 1 month ago

WangResearchLab/SteeringSafety

Viewer • Updated 12 days ago • 71.6k • 370 • 2

updated a collection about 1 month ago

SteeringSafety

Collection

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives • 2 items • Updated 8 days ago • 1

upvoted a collection about 1 month ago

SteeringSafety

Collection

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives • 2 items • Updated 8 days ago • 1

upvoted a paper about 1 month ago

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

Paper • 2509.13450 • Published Sep 16 • 7

updated a collection about 1 month ago

SteeringSafety

Collection

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives • 2 items • Updated 8 days ago • 1

published a dataset 2 months ago

WangResearchLab/SteeringSafety

Viewer • Updated 12 days ago • 71.6k • 370 • 2

updated a dataset 3 months ago

ncrispino/sc-jul-19-25

Viewer • Updated Jul 19 • 71.6k • 79