About

Publications

Newsletter

Join Us

Contact Us

Contact Us

About

Publications

Newsletter

Join Us

Contact Us

Contact Us

About

Publications

Newsletter

Join Us

Contact Us

Contact Us

LAPIS LABS

LAPIS LABS

LAPIS LABS

LAPIS LABS

is a student-led artificial intelligence research group

is a student-led artificial intelligence research group

is a student-led artificial intelligence research group

is a student-led artificial intelligence research group

student artist spotlight: @yoon.s.lee

student artist spotlight: @yoon.s.lee

be novel.

be novel.

student artist spotlight: @yoon.s.lee

be novel.

September 2024: MEDCALC-BENCH has received Oral @ NeurIPS 2024


September 2024: RPO has received Spotlight @ NeurIPS 2024

August 2024: AIR and AIR-BENCH were featured in WIRED

July 2024: TAR was featured in WIRED


July 2024: We are partnering with alphaXiv


July 2024: We presented our work to the National Center for Supercomputing Applications


February 2024: LATS was implemented in LangChain


October 2023: We received the NeurIPS 2023 Scholar Award


October 2023: We presented at Google Research


September 2023: We released a SOTA code generator


July 2023: We received the ICML Early Career Scholarship

—

September 2024: MEDCALC-BENCH has received Oral @ NeurIPS 2024


September 2024: RPO has received Spotlight @ NeurIPS 2024

August 2024: AIR and AIR-BENCH were featured in WIRED

July 2024: TAR was featured in WIRED


July 2024: We are partnering with alphaXiv


July 2024: We presented our work to the National Center for Supercomputing Applications


February 2024: LATS was implemented in LangChain


October 2023: We received the NeurIPS 2023 Scholar Award


October 2023: We presented at Google Research


September 2023: We released a SOTA code generator


July 2023: We received the ICML Early Career Scholarship

—

September 2024: MEDCALC-BENCH has received Oral @ NeurIPS 2024


September 2024: RPO has received Spotlight @ NeurIPS 2024

August 2024: AIR and AIR-BENCH were featured in WIRED

July 2024: TAR was featured in WIRED


July 2024: We are partnering with alphaXiv


July 2024: We presented our work to the National Center for Supercomputing Applications


February 2024: LATS was implemented in LangChain


October 2023: We received the NeurIPS 2023 Scholar Award


October 2023: We presented at Google Research


September 2023: We released a SOTA code generator


July 2023: We received the ICML Early Career Scholarship

—

PUBLICATIONS

11 12 24

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

11 12 24

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

11 12 24

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

11 12 24

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

10 10 24

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data

10 10 24

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data

10 10 24

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data

10 10 24

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data

09 27 24

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

09 27 24

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

09 27 24

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

09 27 24

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

08 01 24

Tamper-Resistant Safeguards for Open-Weight LLMs

08 01 24

Tamper-Resistant Safeguards for Open-Weight LLMs

08 01 24

Tamper-Resistant Safeguards for Open-Weight LLMs

08 01 24

Tamper-Resistant Safeguards for Open-Weight LLMs

07 11 24

AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies

07 11 24

AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies

07 11 24

AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies

07 11 24

AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies

06 26 24

AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

06 26 24

AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

06 26 24

AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

06 26 24

AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

06 21 24

FIRST: Faster Improved Listwise Reranking with Single Token Decoding

06 21 24

FIRST: Faster Improved Listwise Reranking with Single Token Decoding

06 21 24

FIRST: Faster Improved Listwise Reranking with Single Token Decoding

06 21 24

FIRST: Faster Improved Listwise Reranking with Single Token Decoding

06 19 24

MEDCALC-BENCH: Evaluating Large Language Models for Medical Calculations

06 19 24

MEDCALC-BENCH: Evaluating Large Language Models for Medical Calculations

06 19 24

MEDCALC-BENCH: Evaluating Large Language Models for Medical Calculations

06 19 24

MEDCALC-BENCH: Evaluating Large Language Models for Medical Calculations

05 30 24

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters

05 30 24

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters

05 30 24

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters

05 30 24

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters

04 03 24

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning

04 03 24

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning

04 03 24

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning

04 03 24

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning

03 07 24

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

03 07 24

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

03 07 24

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

03 07 24

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

03 03 24

Toward Robust Unlearning for LLMs

03 03 24

Toward Robust Unlearning for LLMs

03 03 24

Toward Robust Unlearning for LLMs

03 03 24

Toward Robust Unlearning for LLMs

02 05 24

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models

02 05 24

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models

02 05 24

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models

02 05 24

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models

02 01 24

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

02 01 24

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

02 01 24

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

02 01 24

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

11 02 23

Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models

11 02 23

Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models

11 02 23

Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models

11 02 23

Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models

08 06 23

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

08 06 23

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

08 06 23

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

08 06 23

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

09 25 23

YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis

09 25 23

YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis

09 25 23

YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis

09 25 23

YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis

09 25 23

FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning

09 25 23

FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning

09 25 23

FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning

09 25 23

FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning

09 25 23

Generative Image Model Benchmark for Reasoning and Representation

09 25 23

Generative Image Model Benchmark for Reasoning and Representation

09 25 23

Generative Image Model Benchmark for Reasoning and Representation

09 25 23

Generative Image Model Benchmark for Reasoning and Representation