Derives inequalities between L1 density distances and mixing-measure discrepancies to obtain posterior contraction rates for Dirichlet process mixtures with unknown shared scale.
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , series =
8 Pith papers cite this work, alongside 1,129 external citations. Polarity classification is still indexing.
8
Pith papers citing it
1,129
external citations · external index
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.
A VLA policy using view-selective visual routing and interaction-aware action MoE improves average success by 27.7% in simulation and 43.3% in real-world bimanual tasks over monolithic baselines.
Task-aware expert grouping derived from family-specific co-activation traces cuts average communication cost 31.39% versus task-agnostic baselines in multi-task MoE inference while maintaining Jain fairness near 1.0.
TextBridgeGNN pre-trains a graph recommender across domains and uses text-similarity edges to move ID-based knowledge into a new domain, improving cross-domain, multi-domain, and zero-shot recommendations.
DS-MTNet uses frequency-constrained source decomposition and reusable information slots to jointly decode three EEG-based cognitive readouts in a driving task, outperforming single-task and multi-task baselines.
Benchmarking in pediatric ICU antimicrobial stewardship shows performance depends mainly on target prevalence and dataset traits rather than model complexity, with sequence models improving precision-recall at 24-hour resolution but showing poorer calibration than tabular models.
An inertial navigation system for bikes fuses mixture-of-experts learning with pedal-to-wheel mechanical constraints to reduce drift, reporting at least 12% accuracy gain and sub-0.5 m/s wheel-speed error on real DiDi ride data.
citing papers explorer
-
Convergence Rates for Latent Mixing Measures in Infinite Homoscedastic Location-Scale Mixture Models
Derives inequalities between L1 density distances and mixing-measure discrepancies to obtain posterior contraction rates for Dirichlet process mixtures with unknown shared scale.
-
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.
-
See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation
A VLA policy using view-selective visual routing and interaction-aware action MoE improves average success by 27.7% in simulation and 43.3% in real-world bimanual tasks over monolithic baselines.
-
Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Inference
Task-aware expert grouping derived from family-specific co-activation traces cuts average communication cost 31.39% versus task-agnostic baselines in multi-task MoE inference while maintaining Jain fairness near 1.0.
-
TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer
TextBridgeGNN pre-trains a graph recommender across domains and uses text-similarity edges to move ID-based knowledge into a new domain, improving cross-domain, multi-domain, and zero-shot recommendations.
-
DS-MTNet:Structured Multi-Task EEG Decoding for Human-Machine Collaboration
DS-MTNet uses frequency-constrained source decomposition and reusable information slots to jointly decode three EEG-based cognitive readouts in a driving task, outperforming single-task and multi-task baselines.
-
Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs
Benchmarking in pediatric ICU antimicrobial stewardship shows performance depends mainly on target prevalence and dataset traits rather than model complexity, with sequence models improving precision-recall at 24-hour resolution but showing poorer calibration than tabular models.
-
Tracking Large-scale Shared Bikes with Inertial Motion Learning in GNSS Blocked Environments
An inertial navigation system for bikes fuses mixture-of-experts learning with pedal-to-wheel mechanical constraints to reduce drift, reporting at least 12% accuracy gain and sub-0.5 m/s wheel-speed error on real DiDi ride data.