arxiv:2508.07616
Aswin Ravikumar Rangsasamy Veerasamy
rrvaswin
·
AI & ML interests
Transformers, SSMs
Recent Activity
upvoted a paper about 9 hours ago
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution published a model about 9 hours ago
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step880 published a model about 9 hours ago
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step1100Organizations
models 130
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step1320
4B • Updated
rrvaswin/qwen3_4b_instruct_icrl_run3_ckpt_step880
4B • Updated
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step1100
4B • Updated
rrvaswin/qwen3_4b_instruct_icrl_run3_ckpt_step660
4B • Updated
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step880
4B • Updated
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step660
4B • Updated
rrvaswin/qwen3_4b_instruct_icrl_run3_ckpt_step440
4B • Updated
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step440
4B • Updated
rrvaswin/qwen3_4b_instruct_icrl_run3_ckpt_step220
4B • Updated
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step220
4B • Updated
datasets 30
rrvaswin/QwQ_64b_Distill
Viewer • Updated • 320k • 18
rrvaswin/qwen2.5_star
Viewer • Updated • 7.43k • 11
rrvaswin/65b_rewarded_top16
Viewer • Updated • 114k • 9
rrvaswin/qwq32b_distill_data_1
Viewer • Updated • 114k • 22
rrvaswin/qwq32b_distill_data
Viewer • Updated • 114k • 27
rrvaswin/qwen_2.5_behaviors_5k
Viewer • Updated • 325k • 225
rrvaswin/qwen_2.5_behaviors
Viewer • Updated • 464k • 165
rrvaswin/analysis_1_to_16
Viewer • Updated • 7.41k • 7
rrvaswin/analysis_1_to_1
Viewer • Updated • 7.41k • 7
rrvaswin/rewarded_16b_gsm8k_incorrect
Viewer • Updated • 77.5k • 5