Jiayu (Mila) Wang
MilaWang
AI & ML interests
Large Language Model, Multimodal Large Language Model, Agentic System, Reasoning, Efficiency
Recent Activity
commented on
a paper
2 days ago
SkillOrchestra: Learning to Route Agents via Skill Transfer authored
a paper
3 days ago
SkillOrchestra: Learning to Route Agents via Skill Transfer upvoted a paper 3 days ago
SkillOrchestra: Learning to Route Agents via Skill Transfer Organizations
models and datasets used in the SparkleRL&SPARKLE project
-
sparkle-reasoning/sparkle_preview
Viewer • Updated • 18k • 49 • 1 -
sparkle-reasoning/SparkleRL-7B-Stage2-aug
Reinforcement Learning • 8B • Updated • 7 • 3 -
sparkle-reasoning/SparkleRL-7B-Stage2-mix
Text Generation • 8B • Updated • 10 -
sparkle-reasoning/SparkleRL-7B-Stage2-hard
Text Generation • 8B • Updated • 9
Model checkpoints and datasets used in the paper Grammar-Aligned Decoding: https://arxiv.org/abs/2405.21047
-
MilaWang/Mistral-7B-Instruct-v0.2-gad-cp-merged
Text Generation • 7B • Updated • 4 -
MilaWang/Mistral-7B-Instruct-v0.2-gad-bv4nogram0-merged
Text Generation • 7B • Updated • 2 -
MilaWang/Mistral-7B-Instruct-v0.2-gad-slianogram3-merged
Text Generation • 7B • Updated • 1 -
MilaWang/Mistral-7B-Instruct-v0.2-gad-cp8-merged
Text Generation • 7B • Updated • 1
models and datasets used in the SparkleRL&SPARKLE project
-
sparkle-reasoning/sparkle_preview
Viewer • Updated • 18k • 49 • 1 -
sparkle-reasoning/SparkleRL-7B-Stage2-aug
Reinforcement Learning • 8B • Updated • 7 • 3 -
sparkle-reasoning/SparkleRL-7B-Stage2-mix
Text Generation • 8B • Updated • 10 -
sparkle-reasoning/SparkleRL-7B-Stage2-hard
Text Generation • 8B • Updated • 9
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models: https://arxiv.org/pdf/2406.14852
Model checkpoints and datasets used in the paper Grammar-Aligned Decoding: https://arxiv.org/abs/2405.21047
-
MilaWang/Mistral-7B-Instruct-v0.2-gad-cp-merged
Text Generation • 7B • Updated • 4 -
MilaWang/Mistral-7B-Instruct-v0.2-gad-bv4nogram0-merged
Text Generation • 7B • Updated • 2 -
MilaWang/Mistral-7B-Instruct-v0.2-gad-slianogram3-merged
Text Generation • 7B • Updated • 1 -
MilaWang/Mistral-7B-Instruct-v0.2-gad-cp8-merged
Text Generation • 7B • Updated • 1