Adaptive scheduling of interventions in discrete diffusion language models, timed to attribute-specific commitment schedules discovered with sparse autoencoders, delivers precise multi-attribute steering up to 93% strength while preserving generation quality.
Bert: Pre-training of deep bidi- rectional transformers for language understanding
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
A large-scale benchmark finds that recent multimodal domain generalization methods give only marginal gains over a plain ERM baseline, with no method winning consistently and all degrading sharply under corruption or missing modalities.
NEST is a nested transformer for sequences of multisets that uses masked set modeling to learn improved set-level representations from hierarchical event streams like EHRs.
CortexMAE adapts Vision Transformers to fMRI via cortical flat maps, shows power-law scaling on 2.1K hours of data, and outperforms priors on cognitive state decoding while failing to beat a simple functional connectivity baseline on subject-level trait prediction.
Action Semantics Learning trains app agents to align with the semantic effects of actions via a Semantic Estimator module, improving robustness to out-of-distribution scenarios over syntax-matching fine-tuning.
CellRefine adds a marker-gene-guided post-pretraining stage to single-cell models that refines the cell embedding manifold and improves downstream task performance by up to 15%.
The survey frames VLA models as pipelines that generate progressively grounded action tokens and classifies those tokens into eight types to guide future development.
citing papers explorer
-
Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
A large-scale benchmark finds that recent multimodal domain generalization methods give only marginal gains over a plain ERM baseline, with no method winning consistently and all degrading sharply under corruption or missing modalities.
-
Scaling Vision Transformers for Functional MRI with Flat Maps
CortexMAE adapts Vision Transformers to fMRI via cortical flat maps, shows power-law scaling on 2.1K hours of data, and outperforms priors on cognitive state decoding while failing to beat a simple functional connectivity baseline on subject-level trait prediction.