Xinyu Zhu's picture

11 10

Xinyu Zhu

TianHongZXY

·

https://zhuxinyu.top

AI & ML interests

Large Language Models; Reasoning; Reinforcement Learning

Recent Activity

published a model 1 day ago

TianHongZXY/Qwen3-4B-Thinking-2507-SFT-10-epochs-synthesized-clear-problems-global_step_280

updated a model 1 day ago

TianHongZXY/Qwen3-4B-Thinking-2507-SFT-10-epochs-synthesized-clear-problems-global_step_280

upvoted a paper about 1 month ago

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

View all activity

Organizations

TianHongZXY 's datasets 58

TianHongZXY/similar_problems_with_three_in_context_problems

Viewer • Updated Sep 4 • 2.16k • 2.39k

TianHongZXY/Top_5_similar_question-NVIDIA-OpenScienceReasoning-2

Viewer • Updated Aug 28 • 2.16k • 4.74k

TianHongZXY/aime-1983-2025

Viewer • Updated Apr 16 • 963 • 25

TianHongZXY/AIME2025

Viewer • Updated Mar 22 • 30 • 580 • 1

TianHongZXY/AIME2024

Viewer • Updated Mar 22 • 30 • 477

TianHongZXY/amc23

Viewer • Updated Mar 22 • 40 • 453

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_1500_to_1600

Viewer • Updated Jan 20 • 100 • 9

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4900_to_5000

Viewer • Updated Jan 19 • 100 • 3

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4800_to_4900

Viewer • Updated Jan 19 • 100 • 6

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4700_to_4800

Viewer • Updated Jan 19 • 100 • 7

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4600_to_4700

Viewer • Updated Jan 19 • 100 • 5

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4500_to_4600

Viewer • Updated Jan 19 • 100 • 7

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4400_to_4500

Viewer • Updated Jan 19 • 100 • 6

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4300_to_4400

Viewer • Updated Jan 19 • 100 • 6

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4200_to_4300

Viewer • Updated Jan 19 • 100 • 5

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4100_to_4200

Viewer • Updated Jan 19 • 100 • 6

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4000_to_4100

Viewer • Updated Jan 19 • 100 • 6

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3900_to_4000

Viewer • Updated Jan 19 • 100 • 7

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3800_to_3900

Viewer • Updated Jan 19 • 100 • 5

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3700_to_3800

Viewer • Updated Jan 19 • 100 • 7

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3600_to_3700

Viewer • Updated Jan 19 • 100 • 5

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3500_to_3600

Viewer • Updated Jan 19 • 100 • 4

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3400_to_3500

Viewer • Updated Jan 19 • 100 • 4

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3300_to_3400

Viewer • Updated Jan 19 • 100 • 4

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3200_to_3300

Viewer • Updated Jan 19 • 100 • 7

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3100_to_3200

Viewer • Updated Jan 19 • 100 • 7

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_3000_to_3100

Viewer • Updated Jan 19 • 100 • 4

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_2900_to_3000

Viewer • Updated Jan 19 • 100 • 3

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_2800_to_2900

Viewer • Updated Jan 19 • 100 • 5

TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_2700_to_2800

Viewer • Updated Jan 19 • 100 • 5