Live Human Feedback in the Training Loop: Aligning Diffusion Models with Real People
• 6
AI & ML interests
RLHF, Model Evaluation, Benchmarks, Data Labeling, Human Feedback, Computer Vision, Image Generation, Video Generation, LLMs, Translations
Recent Activity
View all activity
Articles
Organization Card
Fast human data labeling at scale — rapidata.ai for questions or data inquiries just write to us: info@rapidata.ai
Generative models ranked by real people.
-
Rapidata Benchmarks
📊9Image, video and SVG model benchmarks, ranked by humans
-
Video Physics Benchmark
🧪9World models physics benchmark, ranked by humans
-
Camera Movement Benchmark
🎥8World models camera movement benchmark, ranked by humans
-
SVG Generation Benchmark
🔺9SVG generation benchmark, ranked by humans
The vote data behind every live benchmark on benchmark.ai. One dataset per benchmark.
-
Rapidata/svg-benchmark
Viewer • Updated • 318k • 9.84k • 36 -
Rapidata/relative-camera-movement-human-preference-900k
Viewer • Updated • 22.7k • 178 • 4 -
Rapidata/world-model-physics-human-preference-283k
Viewer • Updated • 22.6k • 1.04k • 5 -
Rapidata/camera-movement-human-preference-324k
Viewer • Updated • 49.4k • 561 • 12
Generative models ranked by real people.
-
Rapidata Benchmarks
📊9Image, video and SVG model benchmarks, ranked by humans
-
Video Physics Benchmark
🧪9World models physics benchmark, ranked by humans
-
Camera Movement Benchmark
🎥8World models camera movement benchmark, ranked by humans
-
SVG Generation Benchmark
🔺9SVG generation benchmark, ranked by humans
The vote data behind every live benchmark on benchmark.ai. One dataset per benchmark.
-
Rapidata/svg-benchmark
Viewer • Updated • 318k • 9.84k • 36 -
Rapidata/relative-camera-movement-human-preference-900k
Viewer • Updated • 22.7k • 178 • 4 -
Rapidata/world-model-physics-human-preference-283k
Viewer • Updated • 22.6k • 1.04k • 5 -
Rapidata/camera-movement-human-preference-324k
Viewer • Updated • 49.4k • 561 • 12
spaces 6
Running
9
Video Physics Benchmark
🧪
World models physics benchmark, ranked by humans
Running
8
Camera Movement Benchmark
🎥
World models camera movement benchmark, ranked by humans
Running
8
Text to Image Benchmark
🖼
Text to Image model benchmark, ranked by humans
Running
9
SVG Generation Benchmark
🔺
SVG generation benchmark, ranked by humans
Running
9
Rapidata Benchmarks
📊
Image, video and SVG model benchmarks, ranked by humans
models 0
None public yet
datasets 74
Rapidata/text-to-image-human-preference-6M
Viewer • Updated • 681k • 76 • 7
Rapidata/relative-camera-movement-human-preference-900k
Viewer • Updated • 22.7k • 178 • 4
Rapidata/camera-movement-human-preference-324k
Viewer • Updated • 49.4k • 561 • 12
Rapidata/Translation-deepseek-llama-mixtral-v-deepl
Viewer • Updated • 845 • 63 • 16
Rapidata/Translation-gpt4o_mini-v-gpt4o-v-deepl
Viewer • Updated • 373 • 45 • 16
Rapidata/text-2-image-Rich-Human-Feedback-32k
Viewer • Updated • 32.5k • 308 • 26
Rapidata/text-2-image-Rich-Human-Feedback
Viewer • Updated • 13k • 835 • 37
Rapidata/10k-human-favorite-number
Viewer • Updated • 11.6k • 261 • 8
Rapidata/world-model-physics-human-preference-283k
Viewer • Updated • 22.6k • 1.04k • 5
Rapidata/svg-benchmark
Viewer • Updated • 318k • 9.84k • 36