arxiv:2604.18574
Salman Rahman PRO
salmannyu
AI & ML interests
Natural Language Processing, Deep Learning, Scalable Oversight, and Language Model Evaluation
Recent Activity
upvoted a paper about 8 hours ago
Understanding Reasoning from Pretraining to Post-Training updated a model 20 days ago
salmannyu/first-mistake-rl-results published a model 20 days ago
salmannyu/first-mistake-rl-resultsOrganizations
models 28
salmannyu/first-mistake-rl-results
Updated
salmannyu/model-checkpoints
Updated
salmannyu/llama_base_thinking_sft_noisy_reward_0_9
Updated
salmannyu/llama_base_thinking_sft_majority_vote_math_1024_sample_8k
Updated
salmannyu/mid_train_llama_52b_thinking_data_effect_math_8_sample
Updated
salmannyu/mid_train_llama_52b_thinking_noisy_reward_math_0.7_sample
Updated
salmannyu/mid_train_llama_52b_thinking_noisy_reward_math_0.9_sample
Updated
salmannyu/mid_train_llama_52b_thinking_majority_vote_math_1024_sample
Updated
salmannyu/mid_train_llama_52b_thinking_data_effect_math_2048_sample
Updated
salmannyu/data_effect_scp_do_llama_3b_2048_sample
Updated
datasets 0
None public yet