xziayro

xziayro's activity

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

upvoted a paper about 10 hours ago

P3-SAM: Native 3D Part Segmentation

Paper • 2509.06784 • Published Sep 8, 2025 • 25

upvoted a paper about 15 hours ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published 1 day ago • 32

upvoted an article about 17 hours ago

view article

Article

Pruna 0.3.2: More OSS Algos, More Ways to Optimize

• 

3 days ago

•

4

upvoted 4 papers 1 day ago

Believe Your Model: Distribution-Guided Confidence Calibration

Paper • 2603.03872 • Published 10 days ago • 36

Training-free Latent Inter-Frame Pruning with Attention Recovery

Paper • 2603.05811 • Published 8 days ago • 13

Multi-Head Low-Rank Attention

Paper • 2603.02188 • Published 11 days ago • 3

Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers

Paper • 2603.10744 • Published 2 days ago • 5

upvoted 3 papers 2 days ago

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion

Paper • 2603.06577 • Published 7 days ago • 43

CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing

Paper • 2603.08589 • Published 4 days ago • 34

HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images

Paper • 2603.02210 • Published 11 days ago • 28

upvoted 3 papers 3 days ago

RealWonder: Real-Time Physical Action-Conditioned Video Generation

Paper • 2603.05449 • Published 8 days ago • 11

WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching

Paper • 2603.06331 • Published 7 days ago • 3

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Paper • 2603.05890 • Published 8 days ago • 81

upvoted a paper 5 days ago

From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors

Paper • 2602.21778 • Published 17 days ago • 14

upvoted a paper 7 days ago

DreamWorld: Unified World Modeling in Video Generation

Paper • 2603.00466 • Published 14 days ago • 16

upvoted a paper 8 days ago

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 9 days ago • 161

upvoted a paper 10 days ago

Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance

Paper • 2603.02175 • Published 11 days ago • 22

upvoted an article 10 days ago

view article

Article

Mixture of Experts (MoEs) in Transformers

• 
• 
• +5

16 days ago

•

132

upvoted 2 papers 11 days ago

UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers

Paper • 2511.20123 • Published Nov 25, 2025 • 18

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Paper • 2602.24286 • Published 14 days ago • 86