sjpark5800/qwen3_8b_instruct_3k_flexprompt_batch_diff_new_bs_64_2.5e-7
9B • Updated • 2
Seojeong Park
sjpark5800
·
AI & ML interests
Multimodal LLM, LLM safety
Recent Activity
upvoted a paper about 14 hours ago
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling submitted a paper 1 day ago
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling authored a paper 2 days ago
PosterForest: Hierarchical Multi-Agent Collaboration for Scientific
Poster GenerationOrganizations
None yet
sjpark5800/qwen3_8b_instruct_3k_flexprompt_batch_diff_new_bs_64_1e-6
9B • Updated • 1
sjpark5800/qwen3_4b_instruct_3k_flexprompt_batch_diff_new_bs_64_5e-7
5B • Updated • 1
sjpark5800/qwen3_4b_instruct_3k_flexprompt_batch_diff_new_bs_64_2.5e-7
5B • Updated • 1
sjpark5800/qwen3_4b_instruct_3k_flexprompt_batch_diff_new_bs_64_1e-6
5B • Updated • 2
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_bs_64_2.5e-7_kl_5e-2
8B • Updated • 3
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_bs_64_2.5e-7_kl_5e-3
8B • Updated • 2
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_bs_64_2.5e-7_kl_1e-3
8B • Updated • 1
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_bs_64_2.5e-7_kl_0.0
8B • Updated • 2
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_dapo_bs_64_5e-7
8B • Updated • 3
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_dapo_bs_64_2.5e-7
8B • Updated • 2
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_dapo_bs_64_1e-7
8B • Updated • 2
sjpark5800/qwen3_8b_thinking_3k_flexprompt_batch_diff_new_bs_64_5e-7
9B • Updated • 2
sjpark5800/qwen3_8b_thinking_3k_flexprompt_batch_diff_new_bs_64_2.5e-7
9B • Updated • 2
sjpark5800/qwen3_8b_thinking_3k_flexprompt_batch_diff_new_bs_64_1e-6
9B • Updated • 1
sjpark5800/qwen3_8b_thinking_3k_flexprompt_batch_diff_bs_64_5e-7
9B • Updated • 1
sjpark5800/qwen3_8b_thinking_3k_flexprompt_batch_diff_bs_64_2.5e-7
9B • Updated • 2
sjpark5800/qwen3_8b_thinking_3k_flexprompt_batch_diff_bs_64_1e-6
9B • Updated • 1
sjpark5800/Perception-Judge-Flex-7B
8B • Updated • 2
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_bs_64_5e-7
8B • Updated • 1
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_bs_64_1e-6
8B • Updated • 3
sjpark5800/qwen2.5_7b_3k_flexprompt_batch_diff_new_bs_64_2.5e-7
8B • Updated • 3
sjpark5800/qwen2.5_7b_3k_flexprompt_batch_diff_new_bs_64_5e-7
8B • Updated • 1
sjpark5800/qwen2.5_7b_3k_flexprompt_batch_diff_new_bs_64_1e-6
8B • Updated • 1
sjpark5800/qwen2.5_7b_3k_flexprompt_batch_diff_bs_64_2.5e-7
8B • Updated • 1