xziayro

xziayro's activity

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

upvoted a paper 4 days ago

DMax: Aggressive Parallel Decoding for dLLMs

Paper • 2604.08302 • Published 5 days ago • 45

upvoted 2 papers 5 days ago

MARS: Enabling Autoregressive Models Multi-Token Generation

Paper • 2604.07023 • Published 6 days ago • 35

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning

Paper • 2604.04746 • Published 6 days ago • 67

upvoted 9 papers 6 days ago

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing

Paper • 2509.26641 • Published Sep 30, 2025 • 4

Woosh: A Sound Effects Foundation Model

Paper • 2604.01929 • Published 12 days ago • 12

Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers

Paper • 2603.27666 • Published 16 days ago • 18

VOID: Video Object and Interaction Deletion

Paper • 2604.02296 • Published 12 days ago • 52

Generative World Renderer

Paper • 2604.02329 • Published 12 days ago • 101

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation

Paper • 2604.03118 • Published 11 days ago • 6

SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

Paper • 2604.04911 • Published 8 days ago • 35

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published 8 days ago • 105

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision

Paper • 2604.04934 • Published 8 days ago • 42

upvoted an article 12 days ago

view article

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

• 
• 
• +5

12 days ago

•

841

upvoted 3 papers 12 days ago

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

Paper • 2603.24414 • Published 20 days ago • 183

Embarrassingly Simple Self-Distillation Improves Code Generation

Paper • 2604.01193 • Published 13 days ago • 36

Universal YOCO for Efficient Depth Scaling

Paper • 2604.01220 • Published 13 days ago • 18

upvoted an article 13 days ago

view article

Article

Mastering Long Contexts in LLMs with KVPress

• 

Jan 23, 2025

•

75

upvoted 3 papers 14 days ago

On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

Paper • 2603.28762 • Published 15 days ago • 25

6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models

Paper • 2603.18742 • Published 26 days ago • 10

DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing

Paper • 2603.28713 • Published 15 days ago • 19