← Back to radar
Observation record / arXiv · 人工智能
Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models
First seen 10/17, 04:20 · Last observed 10/18, 10:21 · Source data is current
Read the original source ↗Title-based outlineCounterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models
Why it mattersResearch metadata links to papers and authors. Read the original for conclusions; publication order is not impact.
30 minutesRank movement—
Building history
1 hourRank movement—
Building history
24 hoursRank movement—
Building history
Publication position history
6 observationsPublication feed in source order. Position changes do not count as heat or momentum.
arXiv metadata CC0; papers retain individual licenses· Author Tianshi Wang, Jingsong Wang, Fengling Li, Jingjing Li, Xin Li, Lei Zhu
View original observation times and ranks
| Observation time (Beijing) | Source position |
|---|---|
| 10/18, 10:21 | 6 |
| 10/18, 04:21 | 6 |
| 10/17, 22:21 | 6 |
| 10/17, 16:21 | 6 |
| 10/17, 10:20 | 6 |
| 10/17, 04:20 | 6 |
Daily aggregate history
| 日期 | Best daily position | Last daily position | Observations |
|---|---|---|---|
| 2026-10-17 | 6 | 6 | 4 |
| 2026-10-18 | 6 | 6 | 2 |