xziayro

xziayro's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers about 5 hours ago

DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

Paper • 2602.16968 • Published 1 day ago • 5

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

Paper • 2602.13515 • Published 7 days ago • 16

upvoted 2 papers 1 day ago

SAM 3D Body: Robust Full-Body Human Mesh Recovery

Paper • 2602.15989 • Published 3 days ago • 9

Optimizing Few-Step Generation with Adaptive Matching Distillation

Paper • 2602.07345 • Published 13 days ago • 6

upvoted a paper 2 days ago

Geometry-Aware Rotary Position Embedding for Consistent Video World Model

Paper • 2602.07854 • Published 12 days ago • 6

upvoted 2 papers 3 days ago

FireRed-Image-Edit-1.0 Techinical Report

Paper • 2602.13344 • Published 8 days ago • 4

BitDance: Scaling Autoregressive Generative Models with Binary Tokens

Paper • 2602.14041 • Published 5 days ago • 39

upvoted 2 articles 4 days ago

view article

Article

Mastering Tensor Dimensions in Transformers

• 

Jan 12, 2025

•

139

view article

Article

KV Cache from scratch in nanoVLM

• 
• 
• +3

Jun 4, 2025

•

112

upvoted a paper 4 days ago

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels

Paper • 2602.11715 • Published 8 days ago • 5

upvoted an article 4 days ago

view article

Article

Custom Kernels for All from Codex and Claude

• 
• 
• +2

8 days ago

•

57

upvoted a paper 4 days ago

Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception

Paper • 2602.11858 • Published 8 days ago • 58

upvoted 4 papers 6 days ago

Voxtral Realtime

Paper • 2602.11298 • Published 9 days ago • 15

T3D: Few-Step Diffusion Language Models via Trajectory Self-Distillation with Direct Discriminative Optimization

Paper • 2602.12262 • Published 8 days ago • 8

PISCO: Precise Video Instance Insertion with Sparse Control

Paper • 2602.08277 • Published 11 days ago • 11

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Paper • 2602.12205 • Published 8 days ago • 78

upvoted a paper 8 days ago

ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation

Paper • 2602.09014 • Published 11 days ago • 3

upvoted 3 papers 10 days ago

SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

Paper • 2602.07803 • Published 12 days ago • 4

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

Paper • 2602.08676 • Published 11 days ago • 66

MOVA: Towards Scalable and Synchronized Video-Audio Generation

Paper • 2602.08794 • Published 11 days ago • 152