DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation
Paper
•
2503.10618
•
Published
•
8
Art Atk
ArtAtk
AI & ML interests
Multimodal Models
Recent Activity
upvoted
a
paper
about 7 hours ago
DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture
Design in Text to Image Generation
upvoted
a
paper
about 8 hours ago
4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large
Language Models
upvoted
a
paper
about 8 hours ago
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency
Distillation
Organizations
None yet
ArtAtk's activity
upvoted
a
paper
about 7 hours ago
upvoted
3
papers
about 8 hours ago
4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models
Paper
•
2503.10437
•
Published
•
7
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
Paper
•
2503.09641
•
Published
•
7
Transformers without Normalization
Paper
•
2503.10622
•
Published
•
26
upvoted
a
paper
1 day ago
upvoted
a
paper
16 days ago
upvoted
2
papers
17 days ago
liked
a
Space
19 days ago
upvoted
a
paper
20 days ago
upvoted
a
paper
26 days ago
upvoted
7
papers
about 1 month ago
FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
Paper
•
2502.05179
•
Published
•
24
QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
Paper
•
2502.05003
•
Published
•
43
Weak-to-Strong Diffusion with Reflection
Paper
•
2502.00473
•
Published
•
22
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Paper
•
2502.04320
•
Published
•
35
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper
•
2502.04128
•
Published
•
25
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
Paper
•
2502.02492
•
Published
•
62
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Paper
•
2502.01061
•
Published
•
189
upvoted
2
papers
about 2 months ago