https://s-sahoo.com/mdlm
AI & ML interests
Research group at Cornell focused on machine learning, generative models, AI for science.
https://github.com/kuleshov-group/e2d2
-
Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
Paper • 2510.22852 • Published • 1 -
kuleshov-group/e2d2-cnndm
Feature Extraction • Updated • 6 -
kuleshov-group/e2d2-wmt
Feature Extraction • Updated • 49 -
kuleshov-group/e2d2-gsm8k-finetune-Qwen3-2B
Feature Extraction • Updated • 9
https://discrete-diffusion-guidance.github.io/
Checkpoints of PlantCAD2 models (https://www.biorxiv.org/content/10.1101/2025.08.27.672609v1)
https://m-arriola.com/bd3lms/
-
kuleshov-group/bd3lm-owt-block_size16
Text Generation • 0.2B • Updated • 702 • 17 -
kuleshov-group/bd3lm-owt-block_size4
Text Generation • 0.2B • Updated • 1.91k • 3 -
kuleshov-group/bd3lm-owt-block_size8
Text Generation • 0.2B • Updated • 393 • 1 -
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper • 2503.09573 • Published • 75
https://caduceus-dna.github.io/
-
Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling
Paper • 2403.03234 • Published • 14 -
kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16
Fill-Mask • 7.73M • Updated • 2.36k • 14 -
kuleshov-group/caduceus-ps_seqlen-1k_d_model-256_n_layer-4_lr-8e-3
Fill-Mask • 1.93M • Updated • 119 • 2 -
kuleshov-group/caduceus-ps_seqlen-1k_d_model-118_n_layer-4_lr-8e-3
Fill-Mask • 471k • Updated • 71 • 1
https://plantcad.github.io
https://s-sahoo.com/mdlm
https://m-arriola.com/bd3lms/
-
kuleshov-group/bd3lm-owt-block_size16
Text Generation • 0.2B • Updated • 702 • 17 -
kuleshov-group/bd3lm-owt-block_size4
Text Generation • 0.2B • Updated • 1.91k • 3 -
kuleshov-group/bd3lm-owt-block_size8
Text Generation • 0.2B • Updated • 393 • 1 -
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper • 2503.09573 • Published • 75
https://github.com/kuleshov-group/e2d2
-
Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
Paper • 2510.22852 • Published • 1 -
kuleshov-group/e2d2-cnndm
Feature Extraction • Updated • 6 -
kuleshov-group/e2d2-wmt
Feature Extraction • Updated • 49 -
kuleshov-group/e2d2-gsm8k-finetune-Qwen3-2B
Feature Extraction • Updated • 9
https://caduceus-dna.github.io/
-
Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling
Paper • 2403.03234 • Published • 14 -
kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16
Fill-Mask • 7.73M • Updated • 2.36k • 14 -
kuleshov-group/caduceus-ps_seqlen-1k_d_model-256_n_layer-4_lr-8e-3
Fill-Mask • 1.93M • Updated • 119 • 2 -
kuleshov-group/caduceus-ps_seqlen-1k_d_model-118_n_layer-4_lr-8e-3
Fill-Mask • 471k • Updated • 71 • 1
https://discrete-diffusion-guidance.github.io/
https://plantcad.github.io
Checkpoints of PlantCAD2 models (https://www.biorxiv.org/content/10.1101/2025.08.27.672609v1)