Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
Paper โข 2606.03748 โข Published โข 15
Gradio-Blocks-Party
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
fcakyonย
authored a
paper 21 days ago
innovation64ย
authored a
paper 22 days ago
innovation64ย
submitted a
paper to Daily Papers 25 days ago
gigantย
authored a
paper about 1 month ago
gigantย
submitted a
paper to Daily Papers about 1 month ago
gigantย
authored a
paper about 2 months ago
fcakyonย
authored a
paper about 2 months ago
Post
156
Let me introduce you to our CVPR 2026 paper!
Today's content moderation systems give you a label: safe or unsafe. They don't tell you what triggered the decision, who is involved, or where in the image it happens. That opacity hurts auditing, breaks adaptation across platforms, and frustrates the human review that responsible deployment demands.
We built SenBen to fix this: the first large-scale scene graph benchmark designed specifically for sensitive content moderation:
- 13,999 annotated frames from 157 movies
- Visual Genome style scene graphs with bounding boxes, attributes, and predicates
- Affective state attributes (pain, fear, aggression, distress) so the model captures not just what is in the frame, but what it means
- 16 safety tags across 5 categories, the broadest taxonomy of any dataset of this kind
A small model that beats much bigger ones:
We distilled a frontier VLM into a compact 241M parameter student built on Florence-2.
On grounded scene graph metrics, the 241M student beats every evaluated VLM except Gemini, and every commercial safety API. It also wins on object detection and captioning across the entire model zoo. It runs at 733 ms per frame on 1.2 GB VRAM, which is 7.6 times faster than the next-best local VLM at zero per-frame cost. The whole benchmark, from dataset creation through all baseline evaluations, is reproducible for under $350.
Project: https://senben.kim/
Paper: SenBen: Sensitive Scene Graphs for Explainable Content Moderation (2604.08819)
Dataset: fcakyon/senben
Code (soon): https://github.com/fcakyon/senben
Today's content moderation systems give you a label: safe or unsafe. They don't tell you what triggered the decision, who is involved, or where in the image it happens. That opacity hurts auditing, breaks adaptation across platforms, and frustrates the human review that responsible deployment demands.
We built SenBen to fix this: the first large-scale scene graph benchmark designed specifically for sensitive content moderation:
- 13,999 annotated frames from 157 movies
- Visual Genome style scene graphs with bounding boxes, attributes, and predicates
- Affective state attributes (pain, fear, aggression, distress) so the model captures not just what is in the frame, but what it means
- 16 safety tags across 5 categories, the broadest taxonomy of any dataset of this kind
A small model that beats much bigger ones:
We distilled a frontier VLM into a compact 241M parameter student built on Florence-2.
On grounded scene graph metrics, the 241M student beats every evaluated VLM except Gemini, and every commercial safety API. It also wins on object detection and captioning across the entire model zoo. It runs at 733 ms per frame on 1.2 GB VRAM, which is 7.6 times faster than the next-best local VLM at zero per-frame cost. The whole benchmark, from dataset creation through all baseline evaluations, is reproducible for under $350.
Project: https://senben.kim/
Paper: SenBen: Sensitive Scene Graphs for Explainable Content Moderation (2604.08819)
Dataset: fcakyon/senben
Code (soon): https://github.com/fcakyon/senben
innovation64ย
authored a
paper 5 months ago
innovation64ย
submitted a
paper to Daily Papers 5 months ago
Paper99ย
authored 2
papers 7 months ago
runtime error
2
#10 opened 7 months ago
by 
liangnanying
hystsย
updated a
Space 7 months ago
nouamanetaziย
posted an update 8 months ago
Post
4961
After training ๐๐ฆ๐จ๐ฅ๐๐๐ on ๐๐๐ ๐๐๐๐๐ฌ for nearly a month, I've come to realize something most people overlook: ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ข๐ฌ ๐ญ๐ก๐ ๐ฆ๐๐ค๐-๐จ๐ซ-๐๐ซ๐๐๐ค ๐๐๐๐ญ๐จ๐ซ ๐ข๐ง ๐๐๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ . ๐ฅ
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
innovation64ย
authored a
paper 9 months ago
TomerBarakย
authored 2
papers 10 months ago
phantomcoder1996ย
authored a
paper about 1 year ago
gigantย
authored a
paper about 1 year ago