HINT-lab/sft_Qwen_Qwen3-1.7B
Viewer • Updated • 7.5k • 7
Huang's INTelligence lab
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
Process Rewards with Learned Reliability
HINT-lab/sft_Qwen_Qwen3-0.6B
Viewer • Updated • 7.5k • 4 • 1
HINT-lab/8B_filtered_data
Viewer • Updated • 6.35k • 21 • 1
HINT-lab/sft_Qwen_Qwen3-0.6B-Base
Viewer • Updated • 7.5k • 9
HINT-lab/R1-Qwen-7B-Distilled-OpenR1-Math
Updated • 3
HINT-lab/one_model_iter3_solver_tuned
Viewer • Updated • 4.64k • 3
HINT-lab/one_model_iter2_solver_tuned
Viewer • Updated • 4.59k • 4
HINT-lab/one_model_iter1_solver_tuned
Viewer • Updated • 4.15k • 9
HINT-lab/qwen38b_solver_v1
Viewer • Updated • 3.46k • 2
HINT-lab/qwen0_6_solver_v1
Viewer • Updated • 2.42k • 3
HINT-lab/qwen3_1_7_solver_v1
Viewer • Updated • 9.69k • 2
HINT-lab/octo3bbase_solver_v1
Viewer • Updated • 1.99k • 2
HINT-lab/oct1bshortbase_solver_v1
Viewer • Updated • 669 • 1
HINT-lab/llama8bi_retrain_solver_v5
Viewer • Updated • 2.29k • 2
HINT-lab/qwen38b_solver_v4
Viewer • Updated • 4
HINT-lab/qwen3_frequent_solver_v3
Viewer • Updated • 4.27k • 6
HINT-lab/qwen3_frequent_solver_v1_v2
Viewer • Updated • 7.51k • 6
HINT-lab/7b_unstop_solver_v2
Viewer • Updated • 5.06k • 3
HINT-lab/qwen3_frequent_solver_v2
Viewer • Updated • 3.58k • 2
HINT-lab/7b_unstop_solver_v1
Viewer • Updated • 4.8k • 3
HINT-lab/solver_penalty_qwen3_v0
Viewer • Updated • 13.6k • 3
HINT-lab/penalty_questioner
Viewer • Updated • 14.2k • 4
HINT-lab/persona_test_v2
Viewer • Updated • 4
HINT-lab/solver_start_from_base_v2
Viewer • Updated • 18k • 2
HINT-lab/persona_test
Viewer • Updated • 8.56k • 4
HINT-lab/solver_v2
Viewer • Updated • 13.9k • 4
HINT-lab/solver_qwen25_v1
Viewer • Updated • 17.9k • 1
HINT-lab/base_start_iter_0_sc
Viewer • Updated • 3.6k • 2
HINT-lab/multimodal-open-r1-8k-verified
Viewer • Updated • 608 • 2
HINT-lab/MultiModal-Pretrain
Viewer • Updated • 173k • 4