Xuyang Liu

xuyang-liu16's activity

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

upvoted a paper 1 day ago

OSWAM: An Effective World Action Model with One-Step Action Generation

Paper • 2610.35850 • Published 10 days ago • 10

upvoted 4 papers 7 days ago

OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images

Paper • 2610.35684 • Published 10 days ago • 59

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

Paper • 2610.32749 • Published 13 days ago • 29

Spectral-Spatial Interpretation

Paper • 2610.21114 • Published 21 days ago • 29

StreamEval: Evaluating Interactive Streaming Video Generation Models

Paper • 2610.28402 • Published 16 days ago • 28

authored 4 papers 20 days ago

EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant

Paper • 2605.10343 • Published May 11

AudioKV: KV Cache Eviction in Efficient Large Audio Language Models

Paper • 2604.06694 • Published Apr 8

Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation

Paper • 2608.01953 • Published Aug 5

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

Paper • 2610.18829 • Published 23 days ago • 54

commented a paper 20 days ago

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

Paper • 2610.18829 • Published 23 days ago • 54 •

5

upvoted a paper 20 days ago

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

Paper • 2610.18829 • Published 23 days ago • 54

liked a dataset 23 days ago

VCLab-PolyU/OmniCompass

Benchmark • Updated about 4 hours ago • 3.18k • 3.49k • 7

upvoted a paper 24 days ago

VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs

Paper • 2610.07987 • Published about 1 month ago • 58

upvoted a paper 5 months ago

Text-Vision Co-Instructed Image Editing

Paper • 2606.16767 • Published Jun 15 • 17

liked a Space 5 months ago

Running on Zero

Agents

523

LocateAnything

💬

523

Detect and highlight objects in images or videos

upvoted a paper 5 months ago

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Paper • 2605.27365 • Published May 26 • 143

authored a paper 8 months ago

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models

Paper • 2505.14454 • Published May 20, 2025 • 2

upvoted a paper 8 months ago

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models

Paper • 2505.14454 • Published May 20, 2025 • 2

liked a dataset 8 months ago

kr-cen/MICo-150K

Viewer • Updated Feb 8 • 149k • 2.39k • 11

upvoted a paper 9 months ago

RynnBrain: Open Embodied Foundation Models

Paper • 2602.14979 • Published Feb 13 • 45