Neural Network Optimization

Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning EACL 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 FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer AAAI 2026 GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection EACL 2026 Gated Temporal Fusion Transformers for Robust Multi-Object Tracking WACV 2026 Generalized Threshold Optimization with Harmony Multi-Threshold Neurons for Accurate ANN-to-SNN Conversion AAAI 2026 GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object Detection AAAI 2026 GraFT: Infusing Pre-trained Transformers with Relational Structure for Time Series Forecasting AAAI 2026 Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization AAAI 2026 High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization WACV 2026 How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression? COLT 2026 I-INR: Iterative Implicit Neural Representations AAAI 2026 Imbalanced Gradients in RL Post-Training of Multi-Task LLMs EACL 2026 Improving Chain-of-Thought for Logical Reasoning via Attention-Aware Intervention EACL 2026 Interpreting Capsule Networks for Image Classification by Routing Path Visualization (Abstract Reprint) AAAI 2026 Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration EACL 2026 Less Is More: Vision Representation Compression for Efficient Video Generation with Large Language Models AAAI 2026 Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving AAAI 2026 LLaVA-UHD v2: Exploiting Hierarchical Vision Granularity in MLLMs via Inverse Semantic Pyramid AAAI 2026 MoLoRA: Boosting LLM-based End-to-end Speech Translation with Mixture of Low-rank Experts AAAI 2026 Neural Architecture and Hyperparameter Selection Through Meta-Learning on Time Series AAAI 2026 Neural Collapse-Informed Initialization with Perturbation Injection in Classification-based Metric Learning AAAI 2026 Neural Video Compression with Reference Hierarchy AAAI 2026 On the Dataless Training of Neural Networks AAAI 2026