SeqLoRA applies bilevel optimization to sequential LoRA adaptation for continual multi-concept text-to-image generation with theoretical bounds on forgetting and interference.
Foundations and trends
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7roles
background 2polarities
background 2representative citing papers
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
Introduces modulated learning for private distributed regression allowing one sample per client via calibrated noise injection on samples and aggregation of transformed representations to achieve unbiased gradients in expectation.
High-volume plaintiff-side counsel in Philadelphia eviction cases scales up filing volume and procedural steps but does not produce a broad premium on adverse tenant outcomes such as default or judgment.
The work gives conditions favoring complete-case over IPW estimators in federated settings with missing data and introduces a multi-model calibrated weighting estimator that is consistent when at least one candidate model is correct at each site.
FedAvg DeepSurv across Lifelines (n=148k, self-report) and Rotterdam Study (n=10k, linked outcomes) raised C-statistics from 0.728 to 0.739 and 0.783 to 0.787 versus local training.
FedAvg matches centralized training accuracy on mammography data split by breast density heterogeneity, showing standard FL can handle this clinical variation without special fixes.
citing papers explorer
-
SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation
SeqLoRA applies bilevel optimization to sequential LoRA adaptation for continual multi-concept text-to-image generation with theoretical bounds on forgetting and interference.
-
Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
-
Modulated learning for private and distributed regression with just a single sample per client device
Introduces modulated learning for private distributed regression allowing one sample per client via calibrated noise injection on samples and aggregation of transformed representations to achieve unbiased gradients in expectation.
-
High-Volume Plaintiff-Side Counsel and Single-Appearance Eviction Cases in Philadelphia
High-volume plaintiff-side counsel in Philadelphia eviction cases scales up filing volume and procedural steps but does not produce a broad premium on adverse tenant outcomes such as default or judgment.
-
Federated Learning with Incomplete Data: When to Use Complete Cases and When to Weight
The work gives conditions favoring complete-case over IPW estimators in federated settings with missing data and introduces a multi-model calibrated weighting estimator that is consistent when at least one candidate model is correct at each site.
-
Federated Deep Learning for Privacy-Preserving Cardiovascular Disease Risk Prediction
FedAvg DeepSurv across Lifelines (n=148k, self-report) and Rotterdam Study (n=10k, linked outcomes) raised C-statistics from 0.728 to 0.739 and 0.783 to 0.787 versus local training.
-
Evaluating Federated Learning approaches for mammography under breast density heterogeneity
FedAvg matches centralized training accuracy on mammography data split by breast density heterogeneity, showing standard FL can handle this clinical variation without special fixes.