arxiv:2507.21183
Yuwei Zhang
YWZBrandon
AI & ML interests
None yet
Organizations
models 188
YWZBrandon/memory_summary_qwen3_4b_tpmax5
Updated
YWZBrandon/verl_agent_swebench_sum_reward_v2_grpo_qwen3_4b_qmax_pv5_2048_sft_v2_grp16_max40_s35
Updated
YWZBrandon/verl_agent_swebench_sum_reward_v2_grpo_qwen3_4b_glm_pv5_2048_sft_v2_grp16_max40_s35
Updated
YWZBrandon/verl_agent_swebench_t100_sum_v1_grpo_qwen3_4b_temp1_pv5_2048_sft_v2_grp16_s150
Updated
YWZBrandon/summary-sft-qwen3-4b
4B • Updated • 852
YWZBrandon/exp_qwen35_9b_full_python_sft_checkpoint_200
9B • Updated • 5
YWZBrandon/grpo_trunc1_qwen3_8b_20steps_nopenalty_ckpt150
8B • Updated • 3
YWZBrandon/google_t5-v1_1-large_full_upsample1000
0.8B • Updated • 5
YWZBrandon/google_flan-t5-base_temporal_10_clusters_6_full_upsample1000
0.2B • Updated • 7
YWZBrandon/wikidyk-scope-clf-deberta-v3-large-temporal_10_clusters
Text Classification • 0.4B • Updated • 12
datasets 10
YWZBrandon/browsecomp-trajectories
Viewer • Updated • 18.6k • 1.39k
YWZBrandon/summary_sft_data_v1
Viewer • Updated • 4k • 26
YWZBrandon/r2e-gym-train-trajectories
Preview • Updated • 127
YWZBrandon/lcb_v6_resplit_v2
Viewer • Updated • 1.06k • 28
YWZBrandon/lcb_v6_resplit
Viewer • Updated • 631 • 34
YWZBrandon/searchr1-data
Viewer • Updated • 221k • 43
YWZBrandon/webshop-data
Updated • 74.7k • 3
YWZBrandon/wikidyk
Viewer • Updated • 12.3k • 68 • 2
YWZBrandon/wikidyk_eval_results
Updated • 71
YWZBrandon/wikidyk_exp
Preview • Updated • 39 • 1