Unverified50% confidenceBenchmarkExact time
The adversarially trained SEMA-Auto's average ASR@1 on HarmBench is 13.8 percentage points higher than the previous SOTA.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedShivacon-Energy's LoRA fine-tuning configuration is rank 16, alpha 32, with about 8.8 million trainable parameters (1.75% of the model), 1596 rows of training data, trained on a Google Colab T4 for 300 steps, 3 epochs, learning rate 2e-4, training loss 0.4018, validation loss 0.08377.54% similarUnverifiedAfter training on the Yamaha-CMU Off-Road (YCOR) dataset, SegFormer-B2 achieves a validation set mIoU of approximately 57.4%.54% similarUnverifiedpplx-decider-v1-27b achieved an average score of 85.7% across 11 benchmarks, outperforming the comparison target Jev (official data).51% similarUnverifiedIn the Automation Bench test, the score improved from Cell's 8.1 to Astra's 41.4, and the CAD task score improved from 83.3 to 95.9.50% similarUnverifiedIn the secondary test, SPreCap-e03 with χ1 set to 1.03 achieved a 5.28% test error rate on 100-layer MNIST, versus 6.36% for SELU, with a Holm-corrected p-value of 0.0064 and 13 of 15 seeds performing better.50% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1103178API
curl https://kongchang.com/api/v1/knowledge/claims/1103178MCP
get_claim(id=1103178)