Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning
Paper
• 2601.21037 • Published
• 15
VIBE
community
AI & ML interests
None defined yet.
Recent Activity
chengzu
submitted a paper to Daily Papers 21 days ago
huanyu112
submitted a paper to Daily Papers 24 days ago
huanyu112
updated 16 datasets 25 days ago
VIBE-Benchmark/VIBE-Benchmark
Viewer
• Updated
• 2.65k • 408 • 2
VIBE-Benchmark/VIBE-Seedream4.0
Viewer
• Updated
• 1.03k • 31
VIBE-Benchmark/VIBE-Seedream4.5
Viewer
• Updated
• 1.03k • 46
VIBE-Benchmark/OmniGen
Viewer
• Updated
• 1.03k • 52
VIBE-Benchmark/VIBE-Banana-Flash
Viewer
• Updated
• 1.01k • 76
VIBE-Benchmark/VIBE-GPT-Image
Viewer
• Updated
• 1.01k • 139
VIBE-Benchmark/Edit-R1-Qwen-Image-Edit-2509
Viewer
• Updated
• 1.03k • 55
VIBE-Benchmark/Qwen-Image-Edit-2509
Viewer
• Updated
• 1.03k • 79
VIBE-Benchmark/VIBE-Qwen-Image-Edit
Viewer
• Updated
• 934 • 50
VIBE-Benchmark/FLUX2-dev
Viewer
• Updated
• 1.03k • 2.4k
VIBE-Benchmark/OmniGen2
Viewer
• Updated
• 1.03k • 29 • 1
VIBE-Benchmark/UniWorld-V1
Viewer
• Updated
• 1.03k • 27
VIBE-Benchmark/BAGEL
Viewer
• Updated
• 1.03k • 2.29k
VIBE-Benchmark/Step1X-Edit-v1p2
Viewer
• Updated
• 934 • 1.2k • 1
VIBE-Benchmark/BAGEL-think
Viewer
• Updated
• 1.18k • 41
VIBE-Benchmark/VIBE-Banana-Pro
Viewer
• Updated
• 1.02k • 39
huanyu112
updated a collection 26 days ago