Cross-trajectory negative sampling in contrastive predictive objectives causes encoding of slow noise over dynamics; intra-trajectory sampling eliminates the shortcut and recovers dynamical variables even under strong noise.
Conditional contrastive learning for im- proving fairness in self-supervised learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 2polarities
background 2representative citing papers
Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
MoMo conditions contrastive representations and prediction operators on user preferences via FiLM and low-rank modulation to enable continuous modulation of plan safety while preserving inference efficiency.
BISE extracts bias-free subnetworks from conventionally trained models via pruning, enabling debiased operation without retraining or additional data.
citing papers explorer
-
Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
Cross-trajectory negative sampling in contrastive predictive objectives causes encoding of slow noise over dynamics; intra-trajectory sampling eliminates the shortcut and recovers dynamical variables even under strong noise.
-
Multi-Objective Exploration and Preference Optimization via Mutual Information
Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
-
MoMo: Conditioned Contrastive Representation Learning for Preference-Modulated Planning
MoMo conditions contrastive representations and prediction operators on user preferences via FiLM and low-rank modulation to enable continuous modulation of plan safety while preserving inference efficiency.
-
Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models
BISE extracts bias-free subnetworks from conventionally trained models via pruning, enabling debiased operation without retraining or additional data.