Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
Title resolution pending
4 Pith papers cite this work, alongside 69 external citations. Polarity classification is still indexing.
4
Pith papers citing it
69
external citations · external index
citation-role summary
background 1
method 1
citation-polarity summary
fields
cs.LG 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
TOFU loss mitigates the narrowing of generative diversity in LLMs after supervised fine-tuning by addressing neglect of low-frequency patterns and forgetting of prior knowledge.
L2C2 is a deep RL framework that learns to clean tabular data by aligning it to the synthetic prior of tabular foundation models, yielding higher accuracy on some benchmarks and cross-dataset policy transfer.
Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.
citing papers explorer
-
Toward Calibrated, Fair, and accurate Deepfake Detection
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
-
Diversity in Large Language Models under Supervised Fine-Tuning
TOFU loss mitigates the narrowing of generative diversity in LLMs after supervised fine-tuning by addressing neglect of low-frequency patterns and forgetting of prior knowledge.
-
Prior-Aligned Data Cleaning for Tabular Foundation Models
L2C2 is a deep RL framework that learns to clean tabular data by aligning it to the synthetic prior of tabular foundation models, yielding higher accuracy on some benchmarks and cross-dataset policy transfer.
-
Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation
Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.