arxiv:2603.25158
Jingwei Ni
JingweiNi
AI & ML interests
Claim verification, Causal NLP, NLP for Social Good, NLP for Climate Change
Recent Activity
upvoted a paper about 13 hours ago
Mosaic: Multi-Session Agentic Reinforcement Learning updated a dataset about 1 month ago
JingweiNi/survival-fusion-tcga600-v3.3Organizations
models 918
JingweiNi/iclr-2action-controller-heads
Updated
JingweiNi/uhead_Olmo-3-7B-Think_DAPO_layer24
Updated
JingweiNi/ReProbe-Qwen3-1.7B-DAPO-block-layer16
Updated • 3
JingweiNi/uhead_claim_Qwen3-8B_fixed_prm_feature_ablation_hs_alllayer_20e
Updated • 2
JingweiNi/ue_manager_Qwen3-32B_hs_5e_fixed_on_stqa_1
Updated
JingweiNi/ue_manager_Qwen3-32B_hs_5e_fixed_on_stqa_2
Updated
JingweiNi/ue_manager_Qwen3-32B_hs_5e_fixed_on_stqa_3
Updated
JingweiNi/ue_manager_Qwen3-32B_hs_5e_fixed_on_stqa_0
Updated
JingweiNi/ue_manager_Qwen3-32B_hs_5e_on_gsm8k
Updated
JingweiNi/ue_manager_Qwen3-32B_hs_5e_on_sciqa
Updated
datasets 473
JingweiNi/survival-fusion-tcga600-v3.3
Preview • Updated • 201
JingweiNi/iclr-2action-controller-chains
Preview • Updated • 129
JingweiNi/Qwen3-1.7B-UHead-Rollouts
Viewer • Updated • 26.8k • 38
JingweiNi/qwen35_2b_prm800k_step10k_sent_qwen36_27b
Viewer • Updated • 1.85k • 15
JingweiNi/qwen35_2b_prm800k_step10k_block_qwen36_27b
Viewer • Updated • 1.85k • 19
JingweiNi/ocr2_hardest10k_k2_lowmed_gpt55pos_qwen35neg_seed20260529
Viewer • Updated • 19.9k • 27 • 1
JingweiNi/ocr2_hardest10k_k2_low_medium_50_50_qwen35_fp8_step10k_seed20260529
Viewer • Updated • 19.9k • 26
JingweiNi/ocr2_hardest10k_k2_medium_valid_qwen35_fp8_step10k
Viewer • Updated • 9.97k • 8
JingweiNi/ocr2_hardest10k_k2_low_qwen35_fp8_step10k
Viewer • Updated • 10k • 6
JingweiNi/ocr2_hardest_questions_10k_k2_think_low_vllm_direct_seed20260527_qwen35_fp8_step10k_annotated
Viewer • Updated • 10k • 6