Loie PRO

Loie's activity

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

updated a model 1 day ago

Loie/SpotSound

Updated 1 day ago • 1

updated a dataset 1 day ago

Loie/SpotSound-Bench

Viewer • Updated 1 day ago • 387 • 47

New activity in Loie/SpotSound-Bench 1 day ago

Dataset files missing

1

#2 opened 24 days ago by

chaubeyG

liked a dataset 2 months ago

maifoundations/VideoOdyssey

Viewer • Updated May 27 • 100 • 1.06k • 8

published a model 4 months ago

Loie/SpotSound

Updated 1 day ago • 1

published a dataset 4 months ago

Loie/SpotSound-Bench

Viewer • Updated 1 day ago • 387 • 47

submitted a paper to Daily Papers 4 months ago

SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding

Paper • 2604.13023 • Published Apr 14 • 1

liked a model 7 months ago

openai/whisper-large-v3

Automatic Speech Recognition • 2B • Updated Aug 12, 2024 • 5.1M • • 6.11k

liked a dataset 7 months ago

nvidia/LongAudio

Preview • Updated Apr 5 • 233 • 25

liked 2 datasets about 1 year ago

m-a-p/OmniInstruct_v1

Viewer • Updated Mar 31, 2025 • 96.1k • 344 • 8

m-a-p/OmniBench

Viewer • Updated Jan 31, 2025 • 1.14k • 255 • 11

New activity in Loie/VGGSound about 1 year ago

invalid compressed data

5

#8 opened over 1 year ago by

ZIHANGLIU

liked a dataset about 1 year ago

Loie/KEEP_dataset

Updated Mar 31, 2025 • 21 • 2

liked a Space about 1 year ago

Running

Agents

26

Open LMM Subjective Leaderboard

🌎

26

VLMEvalKit Subjectivce Benchmark Results

New activity in Loie/VGGSound about 1 year ago

Audio Data not Included

3

#9 opened about 1 year ago by

zifuwan

upvoted a paper over 1 year ago

Multi-Agent System for Comprehensive Soccer Understanding

Paper • 2505.03735 • Published May 6, 2025 • 25

updated a dataset over 1 year ago

Loie/KEEP_dataset

Updated Mar 31, 2025 • 21 • 2

liked a model over 1 year ago

Qwen/Qwen2.5-Omni-7B

Any-to-Any • 11B • Updated Apr 30, 2025 • 333k • 1.92k

upvoted a collection over 1 year ago

Qwen2.5-Omni

Collection

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 6 items • Updated Mar 2 • 168

published a dataset over 1 year ago

Loie/KEEP_dataset

Updated Mar 31, 2025 • 21 • 2