Deep Learning › Techniques ›

Model Architecture

4351 directly classified papers

Papers per year

Papers

De-collapsing User Intent: Adaptive Diffusion Augmentation with Mixture-of-Experts for Sequential Recommendation AAAI 2026

Hierarchical Attention Network with Correction for Cross-Domain User Association AAAI 2026

AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer AAAI 2026

Infinity-MoE: Generalizing Mixture of Experts to Infinite Experts EACL 2026

On the Mathematical Relationship Between Layer Normalization and Dynamic Activation Functions EACL 2026

Thesis Proposal: Efficient KV Cache Reuse for Multi-Document Retrieval-Augmented Generation EACL 2026

REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation AAAI 2026

Generalized Threshold Optimization with Harmony Multi-Threshold Neurons for Accurate ANN-to-SNN Conversion AAAI 2026

TDSNNs: Competitive Topographic Deep Spiking Neural Networks for Visual Cortex Modeling AAAI 2026

CoRA: A Collaborative Robust Architecture with Hybrid Fusion for Efficient Perception AAAI 2026

BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching AAAI 2026

Hilbert Curve-Encoded Rotation-Equivariant Oriented Object Detector with Locality-Preserving Spatial Mapping AAAI 2026

Next Patch Prediction for AutoRegressive Visual Generation AAAI 2026

MRGeo: Robust Cross-View Geo-Localization of Corrupted Images via Spatial and Channel Feature Enhancement AAAI 2026

Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling AAAI 2026

From Paper to Structured JSON: An Agentic AI Workflow for Compliant BMR Digital Transformation EACL 2026

HDGS: Hierarchical Dynamic Gaussian Splatting for Urban Driving Scenes AAAI 2026

NeuPAN: Direct Point Robot Navigation with End-to-End Model-Based Learning (Abstract Reprint) AAAI 2026

SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training WACV 2026

BAFLE-DCT: Bypassing Adversarial Filters via Frequency-Selective Embedding in the DCT Domain WACV 2026

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026

Emotion Recognition in Multi-Speaker Conversations through Speaker Identification, Knowledge Distillation, and Hierarchical Fusion EACL 2026

Parameter-Efficient Adaptation of Self-Supervised Models for Arabic Speech Recognition EACL 2026

T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground EACL 2026

Trainable, Multiword-aware Linguistic Tokenization Using Modern Neural Networks EACL 2026