Tianjian Li

dogtooth

·

https://tianjianl.github.io

tianjianl

AI & ML interests

None yet

Recent Activity

liked a dataset 8 days ago

facebook/hackbench

upvoted a paper 16 days ago

Into the Unknown: Benchmarking AI agents on open scientific research problems

upvoted a paper about 1 month ago

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

View all activity

Organizations

dogtooth 's datasets 46

dogtooth/reasoning_state_rl

Viewer • Updated Mar 19 • 262k • 20

dogtooth/rc-annotated-sft

Viewer • Updated Mar 13 • 1.49k • 3

dogtooth/polaris_filtered_removed_all_correct

Viewer • Updated Feb 24 • 38.1k • 8

dogtooth/polaris_filtered_less_than_half_correct

Viewer • Updated Feb 24 • 13.8k • 3

dogtooth/llm_tool_self_context_management_sft

Viewer • Updated Feb 20 • 12.4k • 10

dogtooth/tool_call_truncated_synthesized_traj

Viewer • Updated Feb 17 • 4.54k • 10

dogtooth/tool_verify_truncated

Viewer • Updated Feb 17 • 2.85k • 10

dogtooth/math_training_24k

Viewer • Updated Nov 11, 2025 • 23.9k • 17

dogtooth/Big-Math-RL-Verified

Viewer • Updated Apr 3, 2025 • 1.52M • 65

dogtooth/default_project_dev_test

Viewer • Updated Mar 26, 2025 • 4k • 13

dogtooth/Big-Math-Selected-500

Viewer • Updated Mar 25, 2025 • 3.5k • 43

dogtooth/Big-Math-RL-Verified-Chinese

Viewer • Updated Mar 6, 2025 • 251k • 331

dogtooth/mmlu

Viewer • Updated Mar 5, 2025 • 14.2k • 59

dogtooth/boolq

Viewer • Updated Mar 5, 2025 • 3.27k • 4

dogtooth/gpqa

Viewer • Updated Mar 5, 2025 • 448 • 46

dogtooth/math_qa

Viewer • Updated Mar 5, 2025 • 2.99k • 12

dogtooth/wiqa

Viewer • Updated Mar 5, 2025 • 3k • 119 • 1

dogtooth/pubmed_qa

Viewer • Updated Mar 5, 2025 • 500 • 9

dogtooth/strategyqa

Viewer • Updated Mar 4, 2025 • 687 • 43

dogtooth/aqua_rat

Viewer • Updated Mar 4, 2025 • 254 • 12

dogtooth/quartz

Viewer • Updated Mar 4, 2025 • 784 • 6

dogtooth/sciq

Viewer • Updated Mar 4, 2025 • 1k • 11

dogtooth/art

Viewer • Updated Mar 4, 2025 • 1.53k • 3

dogtooth/winogrande

Viewer • Updated Mar 4, 2025 • 1.27k • 6

dogtooth/truthful_qa

Viewer • Updated Mar 4, 2025 • 817 • 5

dogtooth/social_i_qa

Viewer • Updated Mar 4, 2025 • 1.95k • 57

dogtooth/piqa

Viewer • Updated Mar 4, 2025 • 1.84k • 9

dogtooth/logiqa

Viewer • Updated Mar 4, 2025 • 651 • 79

dogtooth/commonsense_qa

Viewer • Updated Mar 4, 2025 • 1.22k • 12

dogtooth/copa

Viewer • Updated Mar 4, 2025 • 100 • 22