Unverified50% confidenceBenchmarkExact time
Under the zero-shot setting on the TurnBench development set, FD-VAD achieves a maximum EOT recall of 0.853 under the constraint of false positive rate FP≤0.10.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/30/2026
First Seen
Valid until: 12/29/2026
Sources
Related Entities
Related Claims
UnverifiedIf a difficult problem fails across all samples (pass@k ≈ 0), the reward variance is zero, the gradient signal nearly vanishes, and the parameter update approaches zero.67% similarUnverified在100帧生成任务的FVD指标上，欧拉运动引导取得76.18，优于最强基线的79.2067% similarUnverifiedThe framework achieved a precision of 0.82, a recall of 0.85, and an F1 score of 0.82.63% similarUnverifiedAt moderate noise levels and the middle layers of the model, 2 learnable null slots absorbed approximately 90% of the cross-attention mass, while the EOS token's share dropped sharply to approximately 4%.62% similarUnverifiedDuring training, the held-out FID dropped from 33.7 to 27.0, FD-DINOv2 dropped from 570 to 218, and detector-based object accuracy improved from 65% to 90%.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961128API
curl https://kongchang.com/api/v1/knowledge/claims/961128MCP
get_claim(id=961128)