Zijie Xin

xxayt's activity

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

upvoted a paper 24 days ago

Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding

Paper • 2610.16118 • Published 27 days ago • 14

updated a dataset 28 days ago

xxayt/AVUTBenchmark

Viewer • Updated 28 days ago • 1.73k • 167

updated a collection 28 days ago

SEATS

Collection

7 items • Updated 28 days ago • 1

published a dataset 28 days ago

xxayt/AVUTBenchmark

Viewer • Updated 28 days ago • 1.73k • 167

liked a dataset about 1 month ago

qc316/odubench

Viewer • Updated Sep 20 • 2.08k • 1.38k • 6

upvoted a paper about 2 months ago

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

Paper • 2609.13814 • Published Sep 12 • 150

updated a collection 2 months ago

[ICCV2025]MGSV

Collection

[ICCV 2025] Music Grounding by Short Video • 5 items • Updated Sep 7 • 1

updated a dataset 2 months ago

xxayt/MGSV-EC-Raw

Preview • Updated Sep 7 • 7 • 1

published a dataset 2 months ago

xxayt/MGSV-EC-Raw

Preview • Updated Sep 7 • 7 • 1

upvoted a paper 2 months ago

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs

Paper • 2608.21360 • Published Aug 21 • 32

liked a dataset 2 months ago

Alexislhb/Video-IFBench

Viewer • Updated Aug 28 • 706 • 365 • 1

upvoted a paper 2 months ago

WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report

Paper • 2608.24053 • Published Aug 25 • 74

upvoted a collection 2 months ago

WeMM-Embedding

Collection

4 items • Updated 11 days ago • 35

upvoted a paper 3 months ago

Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search

Paper • 2508.02340 • Published Aug 4, 2025 • 1

commented a paper 3 months ago

Stage-adaptive Token Selection for Efficient Omni-modal LLMs

Paper • 2605.20035 • Published May 19 • 8 •

2

upvoted a paper 3 months ago

OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

Paper • 2608.03812 • Published Aug 4 • 18

upvoted a collection 3 months ago

VideoChat3

Collection

10 items • Updated Jul 27 • 27

updated a collection 4 months ago

SEATS

Collection

7 items • Updated 28 days ago • 1

upvoted a paper 5 months ago

OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains

Paper • 2606.14702 • Published Jun 12 • 32

liked a dataset 5 months ago

MiG-NJU/OmniVideo-100K

Viewer • Updated Jun 26 • 200k • 3.35k • 18