CFQ trains quantizer parameters and mixed-precision allocation to preserve counterfactual recourse validity, cost, and direction on Adult, German Credit, and COMPAS while matching accuracy of standard quantizers.
Distilling the knowledge in a neural network
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Residual feature integration with a trainable target-side encoder provably prevents negative transfer, achieving convergence rates no worse than training from scratch under informative target distributions.
RareCP improves interval efficiency for time series conformal prediction by retrieving and weighting regime-specific calibration examples while adapting to drift and maintaining coverage.
Distilling safe refusal behavior from OpenAI o1-mini into Llama-3, Gemma-2, and Qwen3 models via response-based LoRA on multilingual jailbreak data increases jailbreak success rates on MultiJail by up to 16.6 points.
citing papers explorer
-
When Bits Break Recourse: Counterfactual-Faithful Quantization
CFQ trains quantizer parameters and mixed-precision allocation to preserve counterfactual recourse validity, cost, and direction on Adult, German Credit, and COMPAS while matching accuracy of standard quantizers.
-
Residual Feature Integration is Sufficient to Prevent Negative Transfer
Residual feature integration with a trainable target-side encoder provably prevents negative transfer, achieving convergence rates no worse than training from scratch under informative target distributions.
-
RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction
RareCP improves interval efficiency for time series conformal prediction by retrieving and weighting regime-specific calibration examples while adapting to drift and maintaining coverage.
-
Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety
Distilling safe refusal behavior from OpenAI o1-mini into Llama-3, Gemma-2, and Qwen3 models via response-based LoRA on multilingual jailbreak data increases jailbreak success rates on MultiJail by up to 16.6 points.