osunlp/AutoElicit-Exec
Viewer
•
Updated
•
132
•
1
AI & ML interests
Natural language processing, language models, language agents
Recent Activity
View all activity
Papers
When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation
osunlp/AutoElicit-Seed
Viewer
•
Updated
•
361
•
5
osunlp/AutoElicit-Bench
Viewer
•
Updated
•
117
•
4
osunlp/MisActBench
Updated
•
11
•
2
osunlp/TACO-Cobalt-PTB
Viewer
•
Updated
•
184
•
21
osunlp/TACO-Cobalt
Viewer
•
Updated
•
6.1k
•
27
osunlp/GUI-Drag-dataset
Preview
•
Updated
•
70
•
2
osunlp/Online-Mind2Web
Viewer
•
Updated
•
300
•
518
•
22
osunlp/Mind2Web-2
Viewer
•
Updated
•
130
•
145
•
16
osunlp/Mind2Web
Viewer
•
Updated
•
253
•
2.48k
•
123
osunlp/WebGuard
Viewer
•
Updated
•
6k
•
11
•
2
osunlp/AutoSDT-5K
Viewer
•
Updated
•
5.15k
•
56
•
4
osunlp/UGround-V1-Data-Box
Viewer
•
Updated
•
488k
•
59
•
9
osunlp/UGround-V1-Data
Viewer
•
Updated
•
1.23M
•
2.21k
•
22
osunlp/Dreamer-V1-Data
Viewer
•
Updated
•
3.12M
•
146
•
3
osunlp/HippoRAG_2
Preview
•
Updated
•
130
•
6
osunlp/ScienceAgentBench
Viewer
•
Updated
•
102
•
1.72k
•
18
osunlp/SMolInstruct
Updated
•
1.53k
•
50
osunlp/TravelPlanner
Viewer
•
Updated
•
1.23k
•
36.2k
•
77
osunlp/Multimodal-Mind2Web
Viewer
•
Updated
•
14.2k
•
2.97k
•
91
osunlp/TableInstruct
Preview
•
Updated
•
120
•
30
osunlp/KBQA-Agent
Viewer
•
Updated
•
500
•
8
•
9
osunlp/AttributionBench
Viewer
•
Updated
•
63.1k
•
591
•
4
osunlp/ConflictQA
Updated
•
150
•
11
osunlp/MagicBrush
Viewer
•
Updated
•
2.26k
•
1.89k
•
100
osunlp/AttrScore
Viewer
•
Updated
•
1.8M
•
230
•
11