WangLab

university

https://cgraywang.github.io/

chenguangwang

wang-research-lab

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

ncrispino updated a dataset 29 days ago

WangResearchLab/SteeringSafety

ncrispino updated a dataset about 1 month ago

WangResearchLab/SteeringSafety

ncrispino updated a dataset 2 months ago

WangResearchLab/AgentInstruct

View all activity

Papers

Predicting Task Performance with Context-aware Scaling Laws

Budget-aware Test-time Scaling via Discriminative Verification

View all Papers

Collections 5

View 5 collections

models 18

datasets 7

WangResearchLab/SteeringSafety

Viewer • Updated 29 days ago • 84.5k • 1.37k • 3

WangResearchLab/AgentInstruct

Viewer • Updated Oct 20 • 53 • 176 • 2

WangResearchLab/verification-evaluation-data

Viewer • Updated Oct 17 • 1.5k • 25

WangResearchLab/verification-training-problems

Viewer • Updated Oct 17 • 32.5k • 11

WangResearchLab/verification-training-data

Viewer • Updated Oct 17 • 11.4k • 13

WangResearchLab/te_dataset_hf

Viewer • Updated Apr 18 • 1.2k • 68

WangResearchLab/MLAN

Preview • Updated Nov 19, 2024 • 28 • 1

WangLab

AI & ML interests

Recent Activity

Papers

Collections 5

Budget-aware Test-time Scaling via Discriminative Verification

WangResearchLab/verification-training-problems

WangResearchLab/verification-training-data

WangResearchLab/verification-evaluation-data

COSMIC: Generalized Refusal Direction Identification in LLM Activations

RepIt: Representing Isolated Targets to Steer Language Models

SteeringSafety

Budget-aware Test-time Scaling via Discriminative Verification

WangResearchLab/verification-training-problems

WangResearchLab/verification-training-data

WangResearchLab/verification-evaluation-data

COSMIC: Generalized Refusal Direction Identification in LLM Activations

RepIt: Representing Isolated Targets to Steer Language Models

SteeringSafety

models 18

WangResearchLab/verification-1.5b

WangResearchLab/verification-1.5b-thinking

WangResearchLab/Yarn-Llama-2-13b-128k

WangResearchLab/Yarn-Llama-2-13b-64k

WangResearchLab/Yarn-Llama-2-13b-32k

WangResearchLab/Yarn-Llama-2-13b-16k

WangResearchLab/Yarn-Llama-2-13b-8k

WangResearchLab/Llama-2-13b-hf

WangResearchLab/Yarn-Llama-2-7b-128k

WangResearchLab/Yarn-Llama-2-7b-64k

datasets 7

WangResearchLab/SteeringSafety

WangResearchLab/AgentInstruct

WangResearchLab/verification-evaluation-data

WangResearchLab/verification-training-problems

WangResearchLab/verification-training-data

WangResearchLab/te_dataset_hf

WangResearchLab/MLAN

AI & ML interests

Recent Activity

Papers

Team members 3

Collections 5

models 18 Sort: Recently updated

datasets 7 Sort: Recently updated

models 18

datasets 7