127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “routing”

6,157 results

Research

Delta Attention Residuals

DGX agent

arXiv:2605.18855v1 Announce Type: cross Abstract: Attention Residuals replace standard additive residual connections with learned softmax attention over previous layer outputs, enabling selective cros

researcharxiv-cs-cv

20 May 2026

Model Releases

Boundedly Rational Meta-Learning in Sequential Consumer Choice

DGX agent

arXiv:2605.16532v1 Announce Type: new Abstract: Many consumer decisions are repeated choices under uncertainty. Standard models capture these decisions using Bayesian learning and dynamic programming:

Search: “routing”

Delta Attention Residuals

Boundedly Rational Meta-Learning in Sequential Consumer Choice

R2V Agent: Teaching SLMs When to Ask for Help

A Retrieval-Enhanced Transformer for Multi-Step Port-of-Call Sequence Prediction in Global Liner Shipping

Few-Shot Large Language Models for Actionable Triage Categorization of Online Patient Inquiries

SDOF: Taming the Alignment Tax in Multi-Agent Orchestration with State-Constrained Dispatch

RxEval: A Prescription-Level Benchmark for Evaluating LLM Medication Recommendation

SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning

LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices

Echo-LoRA: Parameter-Efficient Fine-Tuning via Cross-Layer Representation Injection

love seeing my discord stay in sync with Hermes Kanban..everything here was done in plain English. I just asked my coordinator to check if w…

PhysEDA: Physics-Aware Learning Framework for Efficient EDA With Manhattan Distance Decay

Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers

From Feasible to Practical: Pareto-Optimal Synthesis Planning

MPD^2-Router: Mask-aware Multi-expert Prior-regularized Dual-head Deferral Router in Glaucoma Screening and Diagnosis

SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis

ARMATA: Auto-Regressive Multi-Agent Task Assignment

Towards Multi-Agent Autonomous Reasoning in Hydrodynamics

Effective Capacitance Modeling Using Graph Neural Networks

Training Non-Differentiable Networks via Optimal Transport

Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training

Flying by Inference: Active Inference World Models for Adaptive UAV Swarms

Optimized Deferral for Imbalanced Settings

RaMP: Runtime-Aware Megakernel Polymorphism for Mixture-of-Experts

DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference

Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling

Rethinking Efficiency in Neural Combinatorial Optimization: Batched Preference Optimization with Mamba

Pay attention to this one, AI devs, especially if you're thinking about agentic commerce or any agent network where many agents share hosts.…

Test-Time Adaptation for Unsupervised Combinatorial Optimization

TRINITY: An Evolved LLM Coordinator https://arxiv.org/abs/2512.04695

260 things we announced at Google Cloud Next '26 – a recap

Doubly Saturated Ramsey Graphs: A Case Study in Computer-Assisted Mathematical Discovery

From Tokens to Concepts: Leveraging SAE for SPLADE

Job Skill Extraction via LLM-Centric Multi-Module Framework

Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation

Task-Dependent Evaluation of LLM Output Homogenization: A Taxonomy-Guided Framework

Adapting Dijkstra for Buffers and Unlimited Transfers

Efficient Mixture-of-Experts LLM Inference with Apple Silicon NPUs

Model-Agnostic Meta Learning for Class Imbalance Adaptation

DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models

Neural Adjoint Method for Meta-optics: Accelerating Volumetric Inverse Design via Fourier Neural Operators

A Two-Stage, Object-Centric Deep Learning Framework for Robust Exam Cheating Detection

Optimize video semantic search intent with Amazon Nova Model Distillation on Amazon Bedrock

Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution

Nucleus-Image: Sparse MoE for Image Generation

Wow. FSD v14.3.1 drove me to 5 destinations that Grok inputted and navigated to with zero interventions. Tesla Self Driving parked and unpar…

Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs