Language, Intelligence, and Model Evaluation Lab

non-profit

https://limenlp.github.io/

limenlp

Activity Feed

AI & ML interests

Natural Language Processing

Recent Activity

zhaihaotian authored a paper 1 day ago

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

MaksimSTW authored a paper 1 day ago

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

linxinso submitted a paper 2 days ago

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

View all activity

Papers

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Video-Based Reward Modeling for Computer-Use Agents

View all Papers

zhaihaotian

authored a paper 1 day ago

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Paper • 2604.10577 • Published 6 days ago • 24

MaksimSTW

authored a paper 1 day ago

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Paper • 2604.10577 • Published 6 days ago • 24

linxinso

submitted a paper to Daily Papers 2 days ago

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Paper • 2604.10577 • Published 6 days ago • 24

Xuwei04

updated a dataset 3 days ago

lime-nlp/OS-Blind

Updated 3 days ago • 22 • 5

Xuwei04

published a dataset 10 days ago

lime-nlp/OS-Blind

Updated 3 days ago • 22 • 5

linxinso

updated 2 collections 16 days ago

Video-Based Reward Modeling for Computer-Use Agents

Collection

A collection of models and datasets from the paper "Video-Based Reward Modeling for Computer-Use Agents". Github: https://github.com/limenlp/ExeVRM • 3 items • Updated 16 days ago • 1

Papers from LIME Lab

Collection

Papers from LIME Lab • 10 items • Updated 16 days ago • 2

MaksimSTW

authored a paper 26 days ago

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published Mar 10 • 43

jieyuz

authored a paper about 1 month ago

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published Mar 10 • 43

HuanxinSheng

authored a paper about 1 month ago

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published Mar 10 • 43

linxinso

authored a paper about 1 month ago

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published Mar 10 • 43

linxinso

submitted a paper to Daily Papers about 1 month ago

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published Mar 10 • 43

linxinso

updated a dataset about 1 month ago

lime-nlp/ExeVR-53k

Updated Mar 12 • 128 • 2

linxinso

updated a model about 1 month ago

lime-nlp/ExeVRM-8B

Video-Text-to-Text • 9B • Updated Mar 12 • 14 • 3

linxinso

published a dataset about 1 month ago

lime-nlp/ExeVR-53k

Updated Mar 12 • 128 • 2

linxinso

published a model about 1 month ago

lime-nlp/ExeVRM-8B

Video-Text-to-Text • 9B • Updated Mar 12 • 14 • 3

MaksimSTW

authored a paper about 1 month ago

DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning

Paper • 2602.18633 • Published Feb 20 • 2

AI & ML interests

Recent Activity

Papers

Team members 9

lime-nlp's activity