arxiv:2603.07392
Jiyeon Kim
jiyeonkim
AI & ML interests
None yet
Recent Activity
authored
a paper
1 day ago
Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition authored
a paper
1 day ago
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams upvoted a paper about 2 months ago
Lost in the Noise: How Reasoning Models Fail with Contextual Distractors Organizations
models 100
jiyeonkim/llava-tulu2sft-vl-dpo_SPA
Image-Text-to-Text • 7B • Updated
jiyeonkim/llava-tulu2sft-vl-dpo_SPAVL
Image-Text-to-Text • 7B • Updated
jiyeonkim/llava-tulu2sft-dpo_safeRLHF-vl
Image-Text-to-Text • 7B • Updated
• 1
jiyeonkim/llava-tulu2sft-dpo_safeRLHF
Text Generation • 7B • Updated
• 3
jiyeonkim/llava-tulu2sft-vl-dpo_safeRLHF
Image-Text-to-Text • 7B • Updated
jiyeonkim/llava-tulu2sft-vl-dpo_dataAug
Image-Text-to-Text • 7B • Updated
jiyeonkim/llava-tulu2sft-vl-dpo
Image-Text-to-Text • 7B • Updated
• 1
jiyeonkim/llava-tulu2sft-ckpt-10200
Image-Text-to-Text • 7B • Updated
• 1
jiyeonkim/llava-tulu2sft-ckpt-8600
Image-Text-to-Text • 7B • Updated
• 1
jiyeonkim/llava-tulu2sft-ckpt-8400
Image-Text-to-Text • 7B • Updated
datasets 10
jiyeonkim/FWE-tokenized-all
Updated
• 421
jiyeonkim/pubmed_random240k_len1k_neox
Viewer
• Updated
• 205k • 8
jiyeonkim/FWE-tokenized-test
Updated
• 2.19k
jiyeonkim/OLMo_C4_data_1k
Viewer
• Updated
• 1.24M • 8
jiyeonkim/c4_hard240k_step5k
Viewer
• Updated
• 205k • 9
jiyeonkim/c4_easy240k_step5k
Viewer
• Updated
• 205k • 56
jiyeonkim/c4_hard240k_step278k
Viewer
• Updated
• 205k • 23
jiyeonkim/c4_easy240k_step278k
Viewer
• Updated
• 205k • 9
jiyeonkim/pubmed_random240k_1k
Viewer
• Updated
• 205k • 7
jiyeonkim/c4_random240k_1k
Viewer
• Updated
• 205k • 7