arxiv:2504.09710
Wentian Zhao
zwt123home123
·
AI & ML interests
None yet
Recent Activity
authored
a paper
25 days ago
DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM
Post-training
upvoted
a
paper
25 days ago
DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM
Post-training
updated
a model
about 1 month ago
zwt123home123/standardtraining_2p_Qwen2.5-7B-Instruct-1M-4ppl_largebs_global_step_320_actor
Organizations
None yet
Papers
2
models
113
zwt123home123/standardtraining_2p_Qwen2.5-7B-Instruct-1M-4ppl_largebs_global_step_320_actor
Updated
•
1
zwt123home123/standardtraining_2p_Qwen2.5-7B-Instruct-1M-4ppl_largebs_global_step_203_actor
Updated
•
1
zwt123home123/standardtraining_2p_Qwen2.5-7B-Instruct-1M-3ppl_largebs_global_step_203_actor
Updated
•
2
zwt123home123/standardtraining_2p_Qwen2.5-7B-Instruct-1M-3ppl_largebs_global_step_400_actor
Updated
•
1
zwt123home123/global_step_840_actor
Updated
•
1
zwt123home123/InternVL2_5-8B
Image-Text-to-Text
•
Updated
•
6
zwt123home123/KV_internvl26b
Updated
zwt123home123/13b_LUT_c100_zpz5_afterrope_nonorm_group_v_cache_640
Updated
zwt123home123/13b_LUT_c100_zpz5_prerope_nonorm_group_v_cache_640
Updated
zwt123home123/attn_weights_save_7b_all_layers_concat_10
Updated
datasets
0
None public yet