-
On-Policy Transition Distillation
Paper • 2610.28048 • Published • 1 -
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain
Text Generation • 2B • Updated • 122 -
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-Mid
Text Generation • 2B • Updated • 121 -
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-Late
Text Generation • 2B • Updated • 125
AI & ML interests
We focus on Natural Language Processing and Multimodal Learning, exploring generative AI across different modalities.
Recent Activity
View all activity
Papers
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory
Organization Card
"EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory"
-
EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory
Paper • 2610.10533 • Published • 9 -
ModalityDance/EngramEdit-LongCat-Flash-Lite-MCF-2K
Text Generation • Updated • 2 -
ModalityDance/EngramEdit-LongCat-Flash-Lite-zsRE-2K
Text Generation • Updated • 1 -
ModalityDance/EngramEdit-LongCat-Flash-Lite-MQuAKE-3K
Text Generation • Updated • 1
-
On-Policy Transition Distillation
Paper • 2610.28048 • Published • 1 -
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain
Text Generation • 2B • Updated • 122 -
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-Mid
Text Generation • 2B • Updated • 121 -
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-Late
Text Generation • 2B • Updated • 125
"EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory"
-
EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory
Paper • 2610.10533 • Published • 9 -
ModalityDance/EngramEdit-LongCat-Flash-Lite-MCF-2K
Text Generation • Updated • 2 -
ModalityDance/EngramEdit-LongCat-Flash-Lite-zsRE-2K
Text Generation • Updated • 1 -
ModalityDance/EngramEdit-LongCat-Flash-Lite-MQuAKE-3K
Text Generation • Updated • 1
models 29
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-ThreeDomain
Text Generation • 2B • Updated • 122
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-7B-Late
Text Generation • 8B • Updated • 133
ModalityDance/OPTD-Qwen3-4B-Late
Text Generation • 4B • Updated • 126
ModalityDance/OPTD-Qwen3-4B-Mid
Text Generation • 4B • Updated • 122
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-Late
Text Generation • 2B • Updated • 125
ModalityDance/OPTD-DeepSeek-R1-Distill-Qwen-1.5B-Mid
Text Generation • 2B • Updated • 121
ModalityDance/EngramEdit-LongCat-Flash-Lite-zsRE-2K
Text Generation • Updated • 1
ModalityDance/EngramEdit-LongCat-Flash-Lite-MCF-2K
Text Generation • Updated • 2
ModalityDance/EngramEdit-LongCat-Flash-Lite-MQuAKE-3K
Text Generation • Updated • 1
ModalityDance/slpo-codi-gpt2
Text Generation • 0.1B • Updated • 23
datasets 5
ModalityDance/CoWorld-Reasoner-Dev
Viewer • Updated • 120 • 56
ModalityDance/PhysTool-Bench
Viewer • Updated • 2.51k • 173
ModalityDance/Optical-Reasoning-4k
Viewer • Updated • 3.91k • 295
ModalityDance/Omni-Bench
Viewer • Updated • 799 • 32 • 1
ModalityDance/AR-Omni-Instruct-v0.1
Viewer • Updated • 481k • 52