xziayro

xziayro's activity

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

upvoted a paper about 13 hours ago

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Paper • 2601.14724 • Published 5 days ago • 71

upvoted an article 6 days ago

view article

Article

Unlocking Longer Generation with Key-Value Cache Quantization

• 

May 16, 2024

•

55

upvoted 3 papers 8 days ago

Transition Matching Distillation for Fast Video Generation

Paper • 2601.09881 • Published 11 days ago • 31

Alterbute: Editing Intrinsic Attributes of Objects in Images

Paper • 2601.10714 • Published 11 days ago • 29

VIBE: Visual Instruction Based Editor

Paper • 2601.02242 • Published 21 days ago • 62

upvoted a paper 12 days ago

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

Paper • 2601.08303 • Published 13 days ago • 16

upvoted a paper 13 days ago

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Paper • 2601.07832 • Published 14 days ago • 51

upvoted 2 papers 14 days ago

GenCtrl -- A Formal Controllability Toolkit for Generative Models

Paper • 2601.05637 • Published 17 days ago • 4

AnyDepth: Depth Estimation Made Easy

Paper • 2601.02760 • Published 20 days ago • 10

upvoted 2 papers 18 days ago

Klear: Unified Multi-Task Audio-Video Joint Generation

Paper • 2601.04151 • Published 19 days ago • 15

Choreographing a World of Dynamic Objects

Paper • 2601.04194 • Published 19 days ago • 13

upvoted 2 papers 19 days ago

DreamStyle: A Unified Framework for Video Stylization

Paper • 2601.02785 • Published 20 days ago • 24

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published 20 days ago • 135

upvoted a paper 20 days ago

LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation

Paper • 2512.23576 • Published 28 days ago • 65

upvoted 2 papers 21 days ago

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Paper • 2601.00664 • Published 24 days ago • 55

NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

Paper • 2601.00393 • Published 25 days ago • 128

upvoted 2 papers 23 days ago

Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

Paper • 2512.23709 • Published 28 days ago • 49

Bridging Your Imagination with Audio-Video Generation via a Unified Director

Paper • 2512.23222 • Published 28 days ago • 6

upvoted a paper 26 days ago

DreamOmni3: Scribble-based Editing and Generation

Paper • 2512.22525 • Published 30 days ago • 15

upvoted a paper 30 days ago

VA-π: Variational Policy Alignment for Pixel-Aware Autoregressive Generation

Paper • 2512.19680 • Published Dec 22, 2025 • 11