This collection hosts SaMer series introduced in paper, Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Langu
Data Mining and Information Systems Lab
dmis-lab
AI & ML interests
None yet
Recent Activity
updated a model about 21 hours ago
dmis-lab/samer-k64-colqwen2 updated a collection about 21 hours ago
SaMer updated a model about 21 hours ago
dmis-lab/samer-k64-colpaliOrganizations
A collection of ablation and final models trained on the Outlier-Safe Pre-Training (OSP) framework.
This collection hosts Meerkat series introduced in paper, Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks.
-
dmis-lab/meerkat-7b-v1.0
Text Generation • 7B • Updated • 149 • • 29 -
dmis-lab/llama-3-meerkat-8b-v1.0
Text Generation • 8B • Updated • 176 • • 9 -
dmis-lab/llama-3-meerkat-70b-v1.0
Text Generation • 71B • Updated • 13 • • 6 -
Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks
Paper • 2404.00376 • Published • 5
This collection hosts models introduced in OLAPH: Improving Factuality in Biomedical Long-form Question Answering.
This collection hosts Phrase-reranker models introduced in TouR (ACL 2023 Findings), optimizing test-time query representations for dense retrieval.
This collection hosts BioBERT (Bioinformatics 2020) series, a domain-specific adaptation of BERT pre-trained on biomedical corpora.
This collection hosts MRPO series introduced in paper, Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
This collection hosts Med-PRM series introduced in paper, Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards
-
dmis-lab/llama-3.1-medprm-reward-v1.0
Text Generation • Updated • 397 • 16 -
dmis-lab/llama-3.1-medprm-reward-raw-training-set
Viewer • Updated • 11.7k • 15 -
dmis-lab/llama-3.1-medprm-reward-training-set
Viewer • Updated • 11.7k • 25 • 11 -
dmis-lab/llama-3.1-medprm-reward-raw-test-set
Viewer • Updated • 5.47k • 9
This collection hosts ANGEL series introduced in paper, Learning from Negative Samples in Generative Biomedical Entity Linking.
This collection hosts models of Self-BioRAG (ISMB 2024), improving medical reasoning through retrieval and self-reflection.
This collection hosts BioSyn (ACL 2020) series, for learning representations of biomedical entities based on their synonyms.
This collection hosts SaMer series introduced in paper, Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Langu
This collection hosts MRPO series introduced in paper, Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
A collection of ablation and final models trained on the Outlier-Safe Pre-Training (OSP) framework.
This collection hosts Med-PRM series introduced in paper, Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards
-
dmis-lab/llama-3.1-medprm-reward-v1.0
Text Generation • Updated • 397 • 16 -
dmis-lab/llama-3.1-medprm-reward-raw-training-set
Viewer • Updated • 11.7k • 15 -
dmis-lab/llama-3.1-medprm-reward-training-set
Viewer • Updated • 11.7k • 25 • 11 -
dmis-lab/llama-3.1-medprm-reward-raw-test-set
Viewer • Updated • 5.47k • 9
This collection hosts Meerkat series introduced in paper, Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks.
-
dmis-lab/meerkat-7b-v1.0
Text Generation • 7B • Updated • 149 • • 29 -
dmis-lab/llama-3-meerkat-8b-v1.0
Text Generation • 8B • Updated • 176 • • 9 -
dmis-lab/llama-3-meerkat-70b-v1.0
Text Generation • 71B • Updated • 13 • • 6 -
Small Language Models Learn Enhanced Reasoning Skills from Medical Textbooks
Paper • 2404.00376 • Published • 5
This collection hosts ANGEL series introduced in paper, Learning from Negative Samples in Generative Biomedical Entity Linking.
This collection hosts models introduced in OLAPH: Improving Factuality in Biomedical Long-form Question Answering.
This collection hosts models of Self-BioRAG (ISMB 2024), improving medical reasoning through retrieval and self-reflection.
This collection hosts Phrase-reranker models introduced in TouR (ACL 2023 Findings), optimizing test-time query representations for dense retrieval.
This collection hosts BioSyn (ACL 2020) series, for learning representations of biomedical entities based on their synonyms.
This collection hosts BioBERT (Bioinformatics 2020) series, a domain-specific adaptation of BERT pre-trained on biomedical corpora.