Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

72144216288 · Jun 202019922001200920182026
48 results for input routing

Capsule networks can only represent symmetric functions due to routing limitations.

problem Capsule networks' expressivity is limited to symmetric functions.
method Proved and empirically demonstrated that EM-routing and routing-by-agreement prevent capsule networks from distinguishing inputs and their negative counterpart.
result Capsule networks are not universal approximators due to the limitation of expressivity.

A dynamic ResNet model learns different routes for images from different classes.

problem Fixed structure in ResNet-like architectures limits their adaptability to diverse inputs.
method Develops a ResNet-based model that dynamically selects Computational Units for each input image.
result Achieves better results on CIFAR-10 test set compared to the original ResNet-38 architecture.

Sparse routing networks with co-training prevent catastrophic forgetting in continual learning.

problem Catastrophic forgetting in neural networks trained on a sequence of tasks.
method Sparse routing networks with co-training to minimize interference between dissimilar tasks.
result Sparse routing networks with co-training outperform densely connected networks on benchmarks.

STAR improves equivariant and invariant representation learning by routing projection heads.

problem Redundant feature learning in equivariant and invariant representation learning.
method Soft Task-Aware Routing (STAR) for projection heads specialization.
result Lower canonical correlations between invariant and equivariant embeddings.

A new dynamic attention model improves vehicle routing problem solutions.

problem Vehicle routing problems (VRP) are NP-hard and challenging to solve.
method Dynamic attention model with a dynamic encoder-decoder architecture.
result The model outperforms previous methods and shows good generalization.

Unified view of context-adaptive inference across statistics, meta-learning, and foundation models.

problem Adapting predictive systems to specific situations.
method Unified framework for context-adaptive inference, bridging statistics, meta-learning, and foundation models.
result Explicit and implicit approaches are mathematically equivalent under certain conditions.

A new capsule network framework that preserves input transformations.

problem Inefficiency in learning part-whole relationships and lack of equivariance guarantees in capsule networks.
method Proposes a new capsule network framework that learns to projectively encode pose-variations for every capsule-type of each layer using a trainable, equivariant function over a grid of group-transformations.
result The proposed framework is equivariant and preserves the compositional representation of an input under transformations.

A new method routes EEG covariance matrices across domains using adaptive subspace selection.

problem Challenges in cross-domain EEG decoding due to distinct SPD manifold regions.
method Dynamic Stiefel routing with expert filters and cross-attention for adaptive subspace projection.
result Consistent gains across three datasets: balanced accuracy improves from 0.773 to 0.823, 0.757 to 0.809, and 0.801 to 0.839.

Theory of MoE Transformers' generalization and scaling.

problem Understanding the generalization and scaling of Mixture-of-Experts (MoE) Transformers.
method Developed a theory that separates active capacity from routing combinatorics, derived a sup-norm covering-number bound, and proved a constructive approximation theorem.
result Generalization and scaling laws for MoE Transformers, showing how active capacity and routing structure affect performance.

Mixtures of neural operators reduce active complexity in operator learning.

problem Reduction of active complexity in operator learning models.
method Constructive comparison between routed mixtures of neural operators (MoNOs) and a fixed single-neural-operator construction.
result Every scalar uniformly continuous nonlinear operator can be approximated by a MoNO whose active expert has smaller depth, width, and rank scaling.

Dynamic information balancing reduces catastrophic forgetting in modular neural networks.

problem Catastrophic forgetting in neural networks when learning multiple tasks.
method Dynamic Information Balancing (DIB) using reinforcement learning to adaptively route inputs based on module information load.
result DIB combined with EWC regularization outperforms models with similar capacity and EWC regularization.

New framework detects adversarial inputs by contrasting human interpretation with classification.

problem Deep neural networks are vulnerable to adversarial inputs, especially in security-critical applications.
method Constructs a detection framework that compares human interpretation with classification results.
result Demonstrates the effectiveness of the new framework through experiments on benchmark datasets.

This paper improves route choice models by incorporating contextual factors.

problem Existing route choice models lack consideration of dynamic contextual conditions.
method Knowledge distillation from Stated Choice Experiments in Immersive Virtual Environment.
result High-fidelity route choice models with increased predictive power.

Researchers share pitfalls and improvements in implementing Hinton's capsule network.

problem Implementation pitfalls in Hinton's capsule network hindered progress in the field.
method Identifying and addressing common mistakes in capsule network implementations.
result Improved implementation of Hinton's capsule network outperforms existing open-source implementations.

Capsule networks improve performance on image classification tasks with fewer parameters.

problem Improving performance of capsule networks with fewer parameters.
method Inverted dot-product attention routing, Layer Normalization, concurrent iterative routing.
result Improves performance on benchmark datasets CIFAR-10 and CIFAR-100, and performs at-par with ResNet-18.

A large GPS dataset reveals that a single route often covers 60% of travel observations.

problem Limited insights from small GPS datasets on route choice behavior.
method Evaluation of path generation algorithms including link penalty, link elimination, simulation, and via-node methods.
result Modified link penalty method achieves 97% coverage, significantly higher than previous studies.

A new method for efficient neural network fine-tuning using queryable low-rank update atoms.

problem Rigidity of static low-rank adaptation methods when input and depth-wise computation vary.
method A shared queryable memory of low-rank update atoms, allowing dynamic and context-sensitive adaptation.
result Improves final test performance and training stability compared to standard low-rank adaptation.

A new router uses attention-based reinforcement learning to solve detailed routing problems efficiently.

problem Solving detailed routing in integrated circuits while adhering to complex design rules.
method Attention-based reinforcement learning applied to track-assignment detailed routing.
result The attention router achieves over 100x acceleration compared to a genetic router without sacrificing solution quality.

Predicts vessel destinations using AIS data and nearest neighbor search.

problem Accurately predict the destination ports and arrival times of vessel trips.
method Partitioned training routes by destination port, use nearest neighbor search, and incorporate improvements like avoiding frequent port changes and automating parameter tuning.
result Significant improvements in prediction accuracy compared to baseline methods.

Optimized deferral improves accuracy in imbalanced settings.

problem Imbalance in expert predictions leads to suboptimal performance in two-stage learning to defer.
method Developed novel cost-sensitive learning algorithms and margin-based loss functions tailored for expert imbalance.
result MILD algorithm shows clear improvements over baselines in image classification and LLM routing tasks.

Project learns to model Capsule Networks' routing procedures for better expressiveness.

problem Limited expressiveness of Capsule Networks' inner routing procedures.
method Proposes two ways to learn the routing procedure as a network parameter.
result Improved expressiveness of Capsule Networks through learned routing procedures.

A new approach integrates inventory prediction and routing optimization for better supply chain management.

problem Optimizing efficient route selection in supply chain management with uncertain inventory demand.
method Decision-focused learning approach using neural networks to directly integrate inventory prediction and routing optimization.
result Direct integration of inventory prediction and routing optimization leads to better supply chain decisions.

Polestar optimizes public transportation routes for efficiency and user satisfaction.

problem Difficulty in finding optimal public transportation routes due to complex networks and dynamic situations.
method Developed a Public Transportation Graph (PTG) and a route search algorithm with station binding and ranking modules.
result Demonstrated superior efficiency and user satisfaction compared to existing systems.

Capsule networks improve at detecting changes in compositionality with routing.

problem Capsule networks struggle with detecting changes in compositionality.
method Introduced a loss function based on routing entropy to improve compositionality.
result Capsule networks with the new loss function better detect changes in compositionality.

This study develops methods to coordinate travel routes to reduce congestion.

problem Coordination of travel routes to reduce urban traffic congestion.
method Developed mathematical approaches to quantify coordination potential and adaptive centroid-based clustering algorithm (ACCA).
result ACCA efficiently forms proper coordination groups for CB-CRM, improving efficiency with minimal performance loss.

Optimizes query routing to LLMs under cost and resource constraints.

problem Non-uniform or adversarial batching in per-query routing methods leads to cost inefficiency.
method Batch-level, resource-aware routing framework that jointly optimizes model assignment for each batch.
result Robust routing framework improves accuracy by 1-14% over non-robust methods.

G5 universal GRAPH-BERT learns graph representations across different datasets.

problem Learning graph representations across diverse graph datasets with distinct input and output configurations.
method G5 introduces a pluggable model architecture with input and output components for each graph data source, connected via a unified layer and fusion layer.
result G5 removes obstacles for cross-graph representation learning and transfer, even for sparse data.

New machine learning pipeline solves dynamic vehicle routing problems efficiently.

problem Efficiently handling same day deliveries in e-commerce logistics.
method Combination of machine learning and combinatorial optimization.
result Ranked first in the EURO Meets NeurIPS Vehicle Routing Competition.