mirlab

university

https://mirlab.yonsei.ac.kr/

https://github.com/mirlab

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

sngwon authored a paper 8 days ago

CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents

sngwon authored a paper 8 days ago

Can visual language models resolve textual ambiguity with visual cues? Let visual puns tell you!

sngwon authored a paper 8 days ago

Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics

View all activity

mirlab's activity

sngwon

authored 4 papers 8 days ago

CLARA: Classifying and Disambiguating User Commands for Reliable Interactive Robotic Agents

Paper • 2306.10376 • Published Jun 17, 2023

Can visual language models resolve textual ambiguity with visual cues? Let visual puns tell you!

Paper • 2410.01023 • Published Oct 1, 2024 • 1

Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics

Paper • 2406.14703 • Published Jun 20, 2024 • 2

VisEscape: A Benchmark for Evaluating Exploration-driven Decision-making in Virtual Escape Rooms

Paper • 2503.14427 • Published 16 days ago • 19

jiwan-chung

authored a paper about 1 month ago

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild

Paper • 2502.14892 • Published Feb 17 • 6

sukim96

authored a paper about 1 month ago

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild

Paper • 2502.14892 • Published Feb 17 • 6

yjyu

authored a paper about 1 month ago

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild

Paper • 2502.14892 • Published Feb 17 • 6

kjunh

authored a paper about 1 month ago

EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild

Paper • 2502.14892 • Published Feb 17 • 6

BootsofLagrangian

updated a dataset 2 months ago

mirlab/aka-llama-korean-dataset-multiturn-raw

Viewer • Updated Jan 31 • 39.4k • 55

BootsofLagrangian

in mirlab/aka-llama-korean-dataset-multiturn-raw 2 months ago

[bot] Conversion to Parquet

#1 opened 2 months ago by

parquet-converter

BootsofLagrangian

published a dataset 2 months ago

mirlab/aka-llama-korean-dataset-multiturn-raw

Viewer • Updated Jan 31 • 39.4k • 55

jiwan-chung

authored a paper 2 months ago

SEAL: Entangled White-box Watermarks on Low-Rank Adaptation

Paper • 2501.09284 • Published Jan 16 • 10

Steamout

authored a paper 2 months ago

SEAL: Entangled White-box Watermarks on Low-Rank Adaptation

Paper • 2501.09284 • Published Jan 16 • 10

BootsofLagrangian

authored 2 papers 2 months ago

Towards Visual Text Design Transfer Across Languages

Paper • 2410.18823 • Published Oct 24, 2024

SEAL: Entangled White-box Watermarks on Low-Rank Adaptation

Paper • 2501.09284 • Published Jan 16 • 10

min99830

authored a paper 4 months ago

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding

Paper • 2411.19527 • Published Nov 29, 2024 • 10

BootsofLagrangian

authored 2 papers 4 months ago

Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics

Paper • 2406.14703 • Published Jun 20, 2024 • 2

TIPO: Text to Image with Text Presampling for Prompt Optimization

Paper • 2411.08127 • Published Nov 12, 2024 • 3

min99830

authored 2 papers 6 months ago

Selective Vision is the Challenge for Visual Reasoning: A Benchmark for Visual Argument Understanding

Paper • 2406.18925 • Published Jun 27, 2024 • 1

CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction

Paper • 2410.01273 • Published Oct 2, 2024 • 10

AI & ML interests

Recent Activity

Team members 19

mirlab's activity

[bot] Conversion to Parquet