VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance
Paper • 2607.14660 • Published • 9
🔄 In a Training Loop
samusenps
samusenps
AI & ML interests
New & Foundational Architectures, World Models, Multi-Modality, Interpretability , High Quality Training Data, Reproducible Open Source
Recent Activity
upvoted a paper 9 days ago
Video = World + Event Stream liked a model about 2 months ago
stepfun-ai/Step-3.7-FlashOrganizations
upvoted 2
papers 9 days ago
liked 16
models about 2 months ago
stepfun-ai/Step-3.7-Flash
Image-Text-to-Text • 201B • Updated • 140k • • 424
nvidia/nemotron-3.5-asr-streaming-0.6b
Automatic Speech Recognition • 0.6B • Updated • 884k • • 942
nvidia/Cosmos3-Nano
16B • Updated • 301k • 318
bosonai/higgs-tts-3-4b
Text-to-Speech • 5B • Updated • 370k • 671
LiquidAI/LFM2.5-8B-A1B
Text Generation • 8B • Updated • 135k • 684
JetBrains/Mellum2-12B-A2.5B-Thinking
Text Generation • 12B • Updated • 5.7k • 324
sapientinc/HRM-Text-1B
Text Generation • 1B • Updated • 26.3k • 804
ideogram-ai/ideogram-4-fp8
Text-to-Image • 9B • Updated • 47.9k • • 714
google/gemma-4-12B-it
Any-to-Any • 12B • Updated • 2.98M • 1.35k
nvidia/LocateAnything-3B
Image-Text-to-Text • 4B • Updated • 1.34M • 2.78k
Supertone/supertonic-3
Text-to-Speech • Updated • 42.5k • 891
NemoStation/Marlin-2B
Video-Text-to-Text • 2B • Updated • 6.65k • 570
meituan-longcat/LongCat-Video-Avatar-1.5
Updated • 1.71k • 682
bytedance-research/Lance
Any-to-Any • Updated • 416 • 1.06k
openbmb/MiniCPM5-1B
Text Generation • 1B • Updated • 560k • 1k
numind/NuExtract3
Image-to-Text • 5B • Updated • 1.21M • 312
liked 2
datasets 3 months ago