liang's picture

2 4

liang PRO

CharlesLi

AI & ML interests

Trustworthy Machine Learning

Recent Activity

upvoted a paper about 2 months ago

LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs

View all activity

Organizations

None yet

CharlesLi 's models 515

CharlesLi/qwen_vl_3b_seedbench_position_3x3blocks_300step

Image-to-Text • 4B • Updated Sep 22 • 3

CharlesLi/qwen_vl_3b_mmbench_position_3x3blocks_300step

Image-to-Text • 4B • Updated Sep 22 • 5

CharlesLi/qwen_vl_3b_contrastive_qa_20_step300

Image-to-Text • 4B • Updated Sep 17 • 6

CharlesLi/qwen_vl_3b_jigsaw_qa_300step

Image-to-Text • 4B • Updated Sep 17 • 5

CharlesLi/qwen_vl_3b_position_3x3blocks_step300

Image-to-Text • 4B • Updated Sep 17 • 4

CharlesLi/qwen_vl_3b_rotation_qa_300step

Image-to-Text • 4B • Updated Sep 17 • 6

CharlesLi/qwen_vl_3b_position_qa_step300

Image-to-Text • 4B • Updated Sep 17 • 6

CharlesLi/graph_prime_3B_step1000

3B • Updated Jul 29 • 4

CharlesLi/graph_prime_3B_step800

3B • Updated Jul 29 • 3

CharlesLi/graph_prime_3B_step600

3B • Updated Jul 29 • 5

CharlesLi/graph_prime_3B_step400

3B • Updated Jul 29 • 4

CharlesLi/graph_prime_3B_step200

3B • Updated Jul 29 • 4

CharlesLi/graph_prime_3B_1000

CharlesLi/graph_prime_3B_800

CharlesLi/graph_prime_3B_600

CharlesLi/graph_prime_3B_400

CharlesLi/graph_prime_3B_200

CharlesLi/G1-Zero-7B

8B • Updated May 16 • 5

CharlesLi/CoT-SFT-7B

Text Generation • 8B • Updated May 13 • 7

CharlesLi/Direct-SFT-7B

Text Generation • 8B • Updated May 13 • 5

CharlesLi/grpo_only_hard_graph_task_sft_cot_bsz8_8192_entropy_0005_150

3B • Updated May 13 • 3

CharlesLi/G1-7B

8B • Updated May 12 • 3

CharlesLi/G1-3B

3B • Updated May 10 • 5

CharlesLi/G1-Zero-3B

3B • Updated May 10 • 5

CharlesLi/Direct-SFT-3B

Text Generation • 3B • Updated May 7 • 7

CharlesLi/CoT-SFT-3B

Text Generation • 3B • Updated May 7 • 6

CharlesLi/graph-sft-full

3B • Updated May 6 • 6

CharlesLi/grpo_5_epoch_graph_task_ins_7B_400

8B • Updated May 4 • 5

CharlesLi/grpo_5_epoch_graph_task_ins_7B_200

8B • Updated May 4 • 3

CharlesLi/grpo_5_epoch_graph_task_ins_bsz16_5120_entropy_0005_200

3B • Updated May 3 • 4