arxiv:2606.00408
XuQixin
Racktic
AI & ML interests
NLP, mutimodel
Recent Activity
updated a dataset 1 day ago
Racktic/alchemy-eval-logs published a dataset 1 day ago
Racktic/alchemy-eval-logs authored a paper 11 days ago
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its MechanismOrganizations
models 10
Racktic/DSGym-models
Updated
Racktic/scientist_7b_all_4o_full_toolset_step10
Updated
Racktic/stage2_qwen_distill_sft
8B • Updated • 1
Racktic/stage2_sft554
8B • Updated • 3
Racktic/stage2_bestrl
8B • Updated • 5
Racktic/stage1_11k_2epoch
8B • Updated • 1
Racktic/stage1_11k_stage2_11k_mix_step400
8B • Updated • 2
Racktic/doc_val
Updated
Racktic/mix_sft_step800
8B • Updated • 3
Racktic/qwen_dedup_top8_dpo_old_math_new_math_syn_olympiads
Updated
datasets 27
Racktic/alchemy-eval-logs
Updated
Racktic/DeepSearch-Attn
Updated • 2.54k
Racktic/dsgym_backup
Updated • 217
Racktic/doc_val_outputs
Preview • Updated • 95
Racktic/ablation_nosyndata_logs
Preview • Updated • 167
Racktic/dude_origin_train
Viewer • Updated • 6k • 16
Racktic/ablation_nosyndata
Preview • Updated • 140
Racktic/zeroRL
Preview • Updated • 132
Racktic/sft554_rl
Preview • Updated • 153
Racktic/novcentric_rl
Preview • Updated • 100