Unchun Yang's picture

Unchun Yang

ucyang

·

https://ucyang.com/

AI & ML interests

None yet

Recent Activity

liked a Space about 1 hour ago

TMElyralab/MuseTalk

upvoted a collection about 6 hours ago

liked a model about 6 hours ago

google/gemma-4-31B-it-qat-q4_0-gguf

View all activity

Organizations

upvoted 3 collections about 6 hours ago

DiffusionGemma

1 item • Updated about 14 hours ago • 22

Gemma 4 QAT Q4_0

19 items • Updated 5 days ago • 107

Gemma 4 QAT Mobile

4 items • Updated 6 days ago • 31

upvoted a paper about 6 hours ago

Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models

Paper • 2606.11167 • Published 1 day ago • 2

upvoted a collection about 6 hours ago

Interactivity Alignment

Full-duplex speech models post-trained with reinforcement learning for improved conversational interactivity. • 4 items • Updated about 21 hours ago • 4

upvoted a paper about 6 hours ago

Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking

Paper • 2509.25787 • Published Jan 27 • 2

upvoted a paper 6 days ago

Audio Interaction Model

Paper • 2606.05121 • Published 8 days ago • 107

upvoted 2 papers 7 days ago

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

Paper • 2604.24954 • Published Apr 27 • 25

Live Music Models

Paper • 2508.04651 • Published Aug 6, 2025 • 2

upvoted a paper 9 days ago

Mellum2 Technical Report

Paper • 2605.31268 • Published 13 days ago • 54

upvoted an article 9 days ago

Article

Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains

JetBrains

•

10 days ago

• 31

upvoted 2 collections 9 days ago

Mellum

Series of code models by JetBrains • 12 items • Updated Oct 1, 2025 • 50

Mellum 2

Mellum2 model weights • 6 items • Updated 10 days ago • 109

upvoted a collection 10 days ago

Cosmos3

Omnimodal World Models for Physical AI • 15 items • Updated 3 days ago • 109

upvoted an article 10 days ago

Article

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

nvidia

•

10 days ago

• 75

upvoted 5 collections 12 days ago

XVLA

X-VLA is a soft-prompted Transformer for cross-embodiment robot learning • 6 items • Updated Dec 4, 2025 • 13

VLA-JEPA

VLA-JEPA model checkpoints (LIBERO, Pretrain, SimplerEnv) • 3 items • Updated 14 days ago • 11

UltraData

Ultra Scale, Ultra Quality, Ultra Coverage • 11 items • Updated 14 days ago • 97

Step-3.5-Flash

step 3.5 models • 9 items • Updated Mar 14 • 40

Step3

2 items • Updated Jul 31, 2025 • 22