Unverified50% confidenceBenchmarkExact time
At the full VTF900 gallery scale (N=900) under non-frontal poses, DPIT-ResNet50 achieves 94.68% AUC and 36.08% TAR@1%FAR.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA single RTX 5090 with LLaDA-2.1-mini + ORL reaches 2,788 tokens/s at NVFP4 precision (single-request decoding, batch size 1).61% similarUnverifiedMobileNetV3 Large 版本在 ImageNet 上达到 75.2% Top-1 精度，推理延迟仅为 ResNet-50 的约 1/561% similarUnverifiedModels at the 9B parameter scale can already complete low-precision fine-tuning on consumer-grade GPUs such as the NVIDIA RTX 4090 (24 GB VRAM).58% similarPartially VerifiedNVFP4 occupies 4 bits per parameter, i.e., 0.5 bytes, theoretically halving weight memory usage and load bandwidth compared with FP8.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074835API
curl https://kongchang.com/api/v1/knowledge/claims/1074835MCP
get_claim(id=1074835)