Deep Learning › Techniques ›

Model Architecture

4351 directly classified papers

Papers per year

Papers

Forgetting Knowledge Localization and Isolation for Continual Forgetting of Pre-trained Vision Models AAAI 2026

How Wide and How Deep? Mitigating Over-squashing of GNNs via Channel Capacity Constrained Estimation AAAI 2026

Learning Topology-Driven Multi-Subspace Fusion for Grassmannian Deep Networks AAAI 2026

FedBRICK: Structural Bias Aware Heterogeneous Foundation Model Federated Tuning AAAI 2026

Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction AAAI 2026

EMAformer: Enhancing Transformer Through Embedding Armor for Time Series Forecasting AAAI 2026

HN-MVTS: HyperNetwork-based Multivariate Time Series Forecasting AAAI 2026

DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic AAAI 2026

Leap of FAITH from GNN-to-MLP: Fairness Aware Inference via DisTillation of GrapH Knowledge AAAI 2026

Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation AAAI 2026

Learning Conjugate Direction Fields for Planar Quadrilateral Mesh Generation AAAI 2026

Efficiently Enhancing Long-term Series Forecasting via Adaptive Lookback with Wavelets AAAI 2026

AdaReason: Progressive Training of Multi-LoRA Adapters for Budget-Adaptive Language Reasoning Models AAAI 2026

Space Alignment Matters: The Missing Piece for Inducing Neural Collapse in Long-Tailed Learning AAAI 2026

Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models AAAI 2026

Beyond the Mean: Fisher-Orthogonal Projection for Natural Gradient Descent in Large Batch Training AAAI 2026

AutoSchA: Automatic Hierarchical Music Representations via Multi-Relational Node Isolation AAAI 2026

Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloning AAAI 2026

TLAGC: Taylor Linear Attention-Guided Graph Convolutions for Revealing Spatial Domains in Spatial Multi-Omics Data AAAI 2026

Vision Transformers Are Circulant Attention Learners AAAI 2026

HiQ-Lip: A Hierarchical Quantum-Classical Method for Global Lipschitz Constant Estimation of ReLU Networks AAAI 2026

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization AAAI 2026

Double Rounding: Nearly Lossless Adaptive Bit Switching for QAT AAAI 2026

PartialNet: Compute Less, Perform Better AAAI 2026

PhysicsCorrect: A Training-Free Approach for Stable Neural PDE Simulations AAAI 2026