xziayro

xziayro's activity

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

upvoted a paper 4 days ago

WorldKV: Efficient World Memory with World Retrieval and Compression

Paper • 2605.22718 • Published 5 days ago • 38

upvoted 2 papers 5 days ago

Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

Paper • 2605.21487 • Published 6 days ago • 21

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond

Paper • 2605.19660 • Published 7 days ago • 39

New activity in Lakonik/AsymFLUX.2-klein-9B 6 days ago

Does it work in edit mode?

2

#5 opened 7 days ago by

xziayro

upvoted a paper 7 days ago

Asymmetric Flow Models

Paper • 2605.12964 • Published 13 days ago • 21

liked 2 models 7 days ago

Hanbo-Cheng/DAWN

Updated Feb 19, 2025 • 7

Lakonik/AsymFLUX.2-klein-9B

Text-to-Image • Updated 12 days ago • 5.5k • 62

upvoted 2 papers 7 days ago

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

Paper • 2605.16839 • Published 10 days ago • 12

Lance: Unified Multimodal Modeling by Multi-Task Synergy

Paper • 2605.18678 • Published 8 days ago • 74

liked 2 models 7 days ago

bytedance-research/Lance

Any-to-Any • Updated about 5 hours ago • 1.91k • 836

Efficient-Large-Model/LongLive-2.0-5B

Text-to-Video • Updated 7 days ago • 21

upvoted a paper 7 days ago

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

Paper • 2605.18739 • Published 8 days ago • 109

liked a model 8 days ago

mvp-lab/RAVEN

Text-to-Video • Updated 11 days ago • 4

upvoted 3 papers 8 days ago

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO

Paper • 2605.15190 • Published 12 days ago • 13

Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning

Paper • 2605.13852 • Published Mar 25 • 25

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published 12 days ago • 82

upvoted 2 papers 12 days ago

Qwen-Image-VAE-2.0 Technical Report

Paper • 2605.13565 • Published 13 days ago • 59

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published 13 days ago • 96

liked a Space 13 days ago

Running on Zero

Agents

Featured

263

Pixal3D

🏆

263

High-fidelity pixel-aligned image-to-3D generation.

upvoted a paper 14 days ago

Pixal3D: Pixel-Aligned 3D Generation from Images

Paper • 2605.10922 • Published 15 days ago • 32