TongZheng PRO
TongZheng1999
AI & ML interests
Natural Language Processing
Recent Activity
upvoted a paper 3 days ago
StyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion upvoted a paper 17 days ago
Questioning the Questions: Sustaining Self-Evolution in Reasoning ModelsOrganizations
models 388
TongZheng1999/Initial-Dual-Reasoning-4B-Iter1-Strong-Init-Filter-step1000
4B • Updated • 3
TongZheng1999/Initial-Dual-Reasoning-4B-Added-Special-Tokens
4B • Updated • 2
TongZheng1999/Initial-Dual-Reasoning-4B
4B • Updated • 6
TongZheng1999/HS_Reasoning_4B_Filter_1_epoch
4B • Updated • 4
TongZheng1999/HS_Model_4B_17k
4B • Updated • 6
TongZheng1999/HS_Model_4B
4B • Updated • 4
TongZheng1999/sft_iter_1_sample_100
Updated
TongZheng1999/test_reasoning_1
0.8B • Updated • 6
TongZheng1999/test_reasoning
0.8B • Updated • 6
TongZheng1999/PF_Qwen-3-4B-Instruct-star-mixed_direct-OP-final_v2_10-2-5Rounds-iter-5
Text Generation • 196k • Updated • 11
datasets 60
TongZheng1999/iter_1_reinforce_baseline_per_sample_200epoch_strong_init_step_150_processed_Merge_f_by_judge
Viewer • Updated • 22.1k • 11
TongZheng1999/iter_1_reinforce_baseline_per_sample_200epoch_strong_init_step_150_processed_filtered_by_judge
Viewer • Updated • 5.43k • 18
TongZheng1999/iter_1_reinforce_baseline_per_sample_200epoch_strong_init_step_150_processed_Merge
Viewer • Updated • 33.4k • 11
TongZheng1999/iter_1_reinforce_baseline_per_sample_200epoch_strong_init_step_150_processed
Viewer • Updated • 16.7k • 15
TongZheng1999/Bespoke-Stratos-17k-Processed
Viewer • Updated • 16.7k • 5
TongZheng1999/iter_1_reinforce_baseline_per_sample_200epoch_strong_init_step_150
Viewer • Updated • 16.7k • 16
TongZheng1999/Bespoke-Stratos-17k-Init-Model-Final-Reinforce-Baseline-Iter1-Strong-Init-Filtered-Merged
Viewer • Updated • 46.5k • 14
TongZheng1999/iter_1_reinforce_baseline_per_sample_200epoch_strong_init_step_150_filtered
Viewer • Updated • 13.1k • 13
TongZheng1999/Reasoning-Gym-Hard
Viewer • Updated • 30 • 19
TongZheng1999/Reasoning-Gym
Viewer • Updated • 30 • 12