neural network optimization

Acceleration of Backpropagation in Linear Layers of Transformer Models Based on Gradient Structure EACL 2026 AdaptViG: Adaptive Vision GNN with Exponential Decay Gating WACV 2026 AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting AAAI 2026 APEX-Q: Arbitrary-dimension Product-EXtension Quantization for Accelerated LLM Deployment (Student Abstract) AAAI 2026 Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness WACV 2026 Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models AAAI 2026 DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes AAAI 2026 Distillation Dynamics: Towards Understanding Feature-Based Distillation in Vision Transformers AAAI 2026 Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning EACL 2026 Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios EACL 2026 DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic AAAI 2026 Efficient Vision Transformers via Token Merging with Head-wise Attention Correction WACV 2026 FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models AAAI 2026 Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning WACV 2026 GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object Detection AAAI 2026 HarmoQ: Harmonized Post-Training Quantization for High-Fidelity Image Super-Resolution AAAI 2026 How to Design and Train Your Implicit Neural Representation for Video Compression WACV 2026 InfoQ: Mixed-Precision Quantization via Global Information Flow AAAI 2026 Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration EACL 2026 Learnable Permutation for Structured Sparsity on Transformer Models AAAI 2026 Less Is More: Rethinking Parameter-Efficient Fine-Tuning from a Subtractive Perspective AAAI 2026 Neural Video Compression with Reference Hierarchy AAAI 2026 ODEt(ODEl): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling WACV 2026 One-Cycle Structured Pruning via Stability-Driven Subnetwork Search WACV 2026 On the Dataless Training of Neural Networks AAAI 2026