rrvaswin/qwen3_4b_instruct_icrl_run5_ckpt_step660
4B • Updated
Aswin Ravikumar Rangsasamy Veerasamy
rrvaswin
·
AI & ML interests
Transformers, SSMs
Recent Activity
updated a model 11 minutes ago
rrvaswin/qwen3_4b_instruct_icrl_run5_ckpt_step660 published a model 12 minutes ago
rrvaswin/qwen3_4b_instruct_icrl_run5_ckpt_step660 updated a model about 7 hours ago
rrvaswin/qwen3_4b_instruct_icrl_run5_ckpt_step440Organizations
updated a
model 11 minutes ago
published a
model 12 minutes ago
updated a
model about 7 hours ago
published a
model about 7 hours ago
updated a
model about 14 hours ago
published a
model about 14 hours ago
authored 3
papers 1 day ago
GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
Paper • 2510.03777 • Published • 2
Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
Paper • 2605.08472 • Published • 5
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
Paper • 2604.03472 • Published • 2
updated a
model 1 day ago
published a
model 1 day ago
upvoted a paper 2 days ago
published 8
models 2 days ago
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step880
4B • Updated
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step1100
4B • Updated
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step1320
4B • Updated
rrvaswin/qwen3_4b_instruct_icrl_run3_ckpt_step880
4B • Updated
rrvaswin/qwen3_4b_instruct_icrl_run3_ckpt_step440
4B • Updated
rrvaswin/qwen3_4b_instruct_icrl_run3_ckpt_step660
4B • Updated
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step660
4B • Updated
rrvaswin/qwen3b_instruct_icrl_run2_ckpt_step440
4B • Updated