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 5 days ago

WangResearchLab/AgentInstruct

kylemontgomery updated a dataset 9 days ago

WangResearchLab/verification-evaluation-data

kylemontgomery updated a collection 9 days ago

Verification

View all activity

Papers

Predicting Task Performance with Context-aware Scaling Laws

Budget-aware Test-time Scaling via Discriminative Verification

View all Papers

WangResearchLab 's collections 5

Verification

Data and verifier from the paper "Budget-aware Test-time Scaling via Discriminative Verification".

Budget-aware Test-time Scaling via Discriminative Verification

Paper • 2510.14913 • Published 9 days ago • 4
WangResearchLab/verification-training-problems

Viewer • Updated 9 days ago • 32.5k • 11
WangResearchLab/verification-training-data

Viewer • Updated 9 days ago • 11.4k • 16
WangResearchLab/verification-evaluation-data

Viewer • Updated 9 days ago • 1.5k • 22

SteeringSafety

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives

WangResearchLab/SteeringSafety

Viewer • Updated 9 days ago • 71.6k • 360 • 2
SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

Paper • 2509.13450 • Published Sep 16 • 7

MLAN

Models and dataset for "MLAN: Language-Based Instruction Tuning Improves Zero-Shot Generalization of Multimodal Large Language Models"

WangResearchLab/llava-mlan-llama2-7b

Text Generation • 7B • Updated Nov 19, 2024
WangResearchLab/llava-mlan-vicuna-7b

Text Generation • 7B • Updated Nov 19, 2024
WangResearchLab/llava-mlan-v-llama2-7b

Text Generation • 7B • Updated Nov 19, 2024
WangResearchLab/llava-mlan-v-vicuna-7b

Text Generation • 7B • Updated Nov 19, 2024

LLM Interpretability

Interpretability papers from Prof. Chenguang Wang's lab at UCSC

COSMIC: Generalized Refusal Direction Identification in LLM Activations

Paper • 2506.00085 • Published May 30 • 2
RepIt: Representing Isolated Targets to Steer Language Models

Paper • 2509.13281 • Published Sep 16 • 4
SteeringSafety

Collection

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives • 2 items • Updated 5 days ago • 1

Context-aware Scaling Laws

Models from "Predicting Task Performance with Context-aware Scaling Laws"

Predicting Task Performance with Context-aware Scaling Laws

Paper • 2510.14919 • Published 9 days ago • 3
WangResearchLab/Llama-2-7b-hf

Text Generation • 7B • Updated Feb 4
WangResearchLab/Yarn-Llama-2-7b-8k

Text Generation • 7B • Updated Feb 4 • 4
WangResearchLab/Yarn-Llama-2-7b-16k

Text Generation • 7B • Updated Feb 4 • 1

Verification

Data and verifier from the paper "Budget-aware Test-time Scaling via Discriminative Verification".

Budget-aware Test-time Scaling via Discriminative Verification

Paper • 2510.14913 • Published 9 days ago • 4
WangResearchLab/verification-training-problems

Viewer • Updated 9 days ago • 32.5k • 11
WangResearchLab/verification-training-data

Viewer • Updated 9 days ago • 11.4k • 16
WangResearchLab/verification-evaluation-data

Viewer • Updated 9 days ago • 1.5k • 22

LLM Interpretability

Interpretability papers from Prof. Chenguang Wang's lab at UCSC

COSMIC: Generalized Refusal Direction Identification in LLM Activations

Paper • 2506.00085 • Published May 30 • 2
RepIt: Representing Isolated Targets to Steer Language Models

Paper • 2509.13281 • Published Sep 16 • 4
SteeringSafety

Collection

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives • 2 items • Updated 5 days ago • 1

SteeringSafety

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives

WangResearchLab/SteeringSafety

Viewer • Updated 9 days ago • 71.6k • 360 • 2
SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

Paper • 2509.13450 • Published Sep 16 • 7

Context-aware Scaling Laws

Models from "Predicting Task Performance with Context-aware Scaling Laws"

Predicting Task Performance with Context-aware Scaling Laws

Paper • 2510.14919 • Published 9 days ago • 3
WangResearchLab/Llama-2-7b-hf

Text Generation • 7B • Updated Feb 4
WangResearchLab/Yarn-Llama-2-7b-8k

Text Generation • 7B • Updated Feb 4 • 4
WangResearchLab/Yarn-Llama-2-7b-16k

Text Generation • 7B • Updated Feb 4 • 1

MLAN

Models and dataset for "MLAN: Language-Based Instruction Tuning Improves Zero-Shot Generalization of Multimodal Large Language Models"

WangResearchLab/llava-mlan-llama2-7b

Text Generation • 7B • Updated Nov 19, 2024
WangResearchLab/llava-mlan-vicuna-7b

Text Generation • 7B • Updated Nov 19, 2024
WangResearchLab/llava-mlan-v-llama2-7b

Text Generation • 7B • Updated Nov 19, 2024
WangResearchLab/llava-mlan-v-vicuna-7b

Text Generation • 7B • Updated Nov 19, 2024

AI & ML interests

Recent Activity

Papers

Team members 3

WangResearchLab 's collections 5