127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

research

29,820 results

Research

Residual Reservoir Memory Networks

DGX agent

arXiv:2508.09925v3 Announce Type: replace-cross Abstract: We introduce a novel class of untrained Recurrent Neural Networks (RNNs) within the Reservoir Computing (RC) paradigm, called Residual Reservo

researcharxiv-cs-ai

1 Jun 2026

Research

Rethinking Sparse Mixture of Experts from a Unified Perspective

DGX agent

arXiv:2503.22996v3 Announce Type: replace Abstract: Sparse Mixture of Experts (SMoE) models scale the capacity of models while maintaining constant computational overhead. SMoE methods fall into two c

research

Residual Reservoir Memory Networks

Rethinking Sparse Mixture of Experts from a Unified Perspective

Retriever Portfolios: A Principled Approach to Adaptive RAG

Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't

Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners

SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling

SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference

Scalable Bayesian Inference for Nonlinear Conservation Laws

Scalable Inference-Time Annealing with Surrogate Likelihood Estimators

Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms

ScaleMAP: Preserving Local Density and Neighborhood Structure in Low-Dimensional Embeddings

Scaling Higher-Order Graph Learning with Maximal Clique Complexes

SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks

Score Broadcast and Decorrelation: A General Framework for Broadcast-Based Credit Assignment

Seeing Fast and Slow: Bimodal 3D Scene Graphs for Open-set Tasks

Self-Certifying Transport MCMC via Dual Spectral-Gap Certificates

Self-Reflective Generation at Test Time

Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models

Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection

ShapDBM: Exploring Decision Boundary Maps in Shapley Space

Shared Doubt: Zero-shot Cross-Lingual Confidence Estimation for Language Models

SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense

Sinkhorn Normalization of Diffusion Kernels

Skin Lesion Classification Based on ResNet-50 Enhanced With Adaptive Spatial Feature Fusion

SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling

SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning

SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation

SMART: SMPLest-X Mesh Adaptation and RAFT Tracking for Soccer Pose Estimation

SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics

Spectral Anatomy of Quantum Gaussian Process Kernels

Speculative Decoding Across Languages

Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism

SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation

Stochastic Gradients under Nuisances

Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding

Student Capacity Moderates Knowledge Distillation Effectiveness: A Systematic Study Across ResNet Teacher-Student Pairs on CIFAR-10

Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models

TASER: Task-Aware Stein Regularisation for Geometry-Driven Robustness

Technical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting

The Download: China’s brain implant ambitions

The Fast Mixing Mechanism for Differential Privacy

The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics

The Inclusion Depth of Pattern Languages: An Open Problem in Algorithmic Learning Theory

The Information Geometry of Softmax: Probing and Steering

The Latin Substrate: How Language Models Represent and Mediate Script Choice

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail

TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments

To Grok Grokking: Provable Grokking in Ridge Regression