Zhenxin Ai

kunkk's activity

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

upvoted a paper 3 days ago

dMoE: dLLMs with Learnable Block Experts

Paper • 2605.30876 • Published 6 days ago • 32

upvoted a paper 6 days ago

EarlyTom: Early Token Compression Completes Fast Video Understanding

Paper • 2605.30010 • Published 7 days ago • 31

authored 2 papers 22 days ago

Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View

Paper • 2503.12553 • Published Mar 16, 2025 • 8

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

Paper • 2605.10977 • Published 26 days ago • 10

upvoted a paper 22 days ago

PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks

Paper • 2605.10977 • Published 26 days ago • 10

upvoted a paper 5 months ago

Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View

Paper • 2503.12553 • Published Mar 16, 2025 • 8

updated a Space 12 months ago

Sleeping

Agents

显著性目标检测Demo

🔍

Analyze images to highlight significant areas

published a Space about 1 year ago

Sleeping

Agents

显著性目标检测Demo

🔍

Analyze images to highlight significant areas

upvoted a paper about 1 year ago

Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models

Paper • 2503.16257 • Published Mar 20, 2025 • 28

liked a model about 1 year ago

Xianzu/Niagara

Updated Mar 18, 2025 • 3