NeuLab @ LTI/CMU

university

https://www.cs.cmu.edu/~neulab/

neulab

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

yueqis updated a dataset 2 days ago

neulab/agent-data-collection

yuexiang96 authored a paper 23 days ago

Small Models Struggle to Learn from Strong Reasoners

yuexiang96 authored a paper 23 days ago

Evaluating Vision-Language Models as Evaluators in Path Planning

View all activity

neulab 's datasets 25

neulab/agent-data-collection

Viewer • Updated 2 days ago • 211k • 303 • 1

neulab/VisualPuzzles

Viewer • Updated Apr 16 • 1.17k • 238 • 9

neulab/PangeaInstruct

Updated Feb 2 • 392 • 85

neulab/MultiUI

Viewer • Updated Nov 22, 2024 • 7.29M • 162 • 45

neulab/PangeaBench-xm100

Updated Nov 3, 2024 • 294

neulab/PangeaBench-xmmmu

Viewer • Updated Nov 3, 2024 • 2.65k • 115 • 2

neulab/PangeaBench-flores

Updated Nov 1, 2024 • 17

neulab/PangeaBench-tydiqa

Viewer • Updated Nov 1, 2024 • 241k • 128

neulab/PangeaBench-xchat

Viewer • Updated Nov 1, 2024 • 400 • 31

neulab/PangeaBench-cvqa

Viewer • Updated Oct 31, 2024 • 10.4k • 44 • 1

neulab/PangeaBench-maxm

Viewer • Updated Oct 31, 2024 • 1.89k • 28

neulab/PangeaBench-marvl

Viewer • Updated Oct 31, 2024 • 11k • 145 • 2

neulab/PangeaBench-xgqa

Viewer • Updated Oct 31, 2024 • 77.3k • 30

neulab/PangeaBench-multilingual-llava-bench

Viewer • Updated Oct 31, 2024 • 600 • 16

neulab/PangeaBench-m3exam

Viewer • Updated Oct 28, 2024 • 2.75k • 39

neulab/Mind2Web_bbox_eval

Updated Oct 18, 2024 • 19 • 3

neulab/Mind2Web_train_llava

Viewer • Updated Oct 18, 2024 • 7.26k • 57 • 2

neulab/wiki_asp

Updated Jan 18, 2024 • 329 • 4

neulab/ted_multi

Updated Jan 18, 2024 • 170 • 4

neulab/ted_hrlr

Updated Jan 18, 2024 • 235

neulab/docprompting-conala

Viewer • Updated Mar 14, 2023 • 36.9k • 130 • 6

neulab/mconala

Viewer • Updated Feb 10, 2023 • 896 • 48 • 2

neulab/odex

Viewer • Updated Feb 10, 2023 • 945 • 86 • 10

neulab/tldr

Viewer • Updated Dec 22, 2022 • 448k • 76 • 12

neulab/conala

Viewer • Updated Oct 20, 2022 • 597k • 914 • 60