adversarial-learning

Tag

Cards List
#adversarial-learning

Sequence prediction under a lying oracle

arXiv cs.LG · yesterday Cached

This paper proposes algorithms for sequential prediction under a lying oracle in stochastic and adversarial settings, proving logarithmic regret bounds for the cost function capturing prediction complexity.

0 favorites 0 likes
#adversarial-learning

Adversarial Learning of Classifier-Free Guidance Schedules

arXiv cs.LG · yesterday Cached

This paper proposes learning dynamic classifier-free guidance schedules for diffusion models using adversarial learning to improve text-to-image generation quality by adapting guidance scales to different states.

0 favorites 0 likes
#adversarial-learning

Linguistic Bias Mitigation for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck

arXiv cs.CL · 2026-07-01 Cached

This paper proposes a linguistic-invariant spoofing detection framework that uses teacher-student adversarial learning and a variational information bottleneck to mitigate linguistic bias, achieving up to a 36.2% relative reduction in equal error rate across nine datasets.

0 favorites 0 likes
#adversarial-learning

A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctions

arXiv cs.CL · 2026-06-30 Cached

Introduces A3M, a framework combining adaptive deep reinforcement learning, adversarial reasoning, and multi-objective reward design for strategic bidding in repeated auctions, achieving 30-40% regret reduction.

0 favorites 0 likes
#adversarial-learning

Correcting Sensor-Induced Distribution Drift with Wasserstein Adversarial Learning

arXiv cs.LG · 2026-06-18 Cached

Proposes a Wasserstein-GAN approach for unsupervised calibration of sensor-induced distribution drifts, validated on tracking detector toy models and simulated calorimeter data with aging effects.

0 favorites 0 likes
#adversarial-learning

High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation

Hugging Face Daily Papers · 2026-06-10 Cached

This paper introduces Z-Image Turbo++, a two-step image generation model distilled from an eight-step teacher using distribution-aligned adversarial learning, step-decoupled parameterization, and end-to-end training with iterative regularization to narrow the quality gap with multi-step generation.

0 favorites 0 likes
#adversarial-learning

Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation

arXiv cs.CL · 2026-05-08 Cached

This paper proposed Distribution-Aligned Adversarial Distillation (DisAAD), a method that uses a lightweight proxy model to estimate uncertainty in black-box LLMs with only 1% of the original model size, achieving reliable quantification without requiring internal parameters or multiple sampling.

0 favorites 0 likes
← Back to home

Submit Feedback