Neural Network Optimization

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD AAAI 2026 On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials COLT 2026 OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval AAAI 2026 Ordered Local Momentum for Asynchronous Distributed Learning Under Arbitrary Delays AAAI 2026 Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers EACL 2026 PT-DCFR: Accelerating and Improving Deep CFR Using Population Based Training (Student Abstract) AAAI 2026 Representation Collapse in Machine Translation Through the Lens of Angular Dispersion EACL 2026 Rethinking Deep Alignment Through the Lens of Incomplete Safety Learning AAAI 2026 Scalable Synthesis of Formally Verified Neural Value Function for Hamilton-Jacobi Reachability Analysis (Abstract Reprint) AAAI 2026 Scaling and Transferability of Annealing Strategies in Large Language Model Training AAAI 2026 Sleep-Like Replay Reduces Loss-Landscape Sharpness to Improve Generalization (Student Abstract) AAAI 2026 Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient WACV 2026 Stabilizing Spiking Neurons Through Biologically Inspired Polarization AAAI 2026 Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding AAAI 2026 Steering Pretrained Drafters During Speculative Decoding AAAI 2026 Step Back to Leap Forward: Self-Backtracking for Symbolic Reasoning and Planning in Language Models AAAI 2026 Super Level Sets and Exponential Decay: A Synergistic Approach to Stable Neural Network Training (Abstract Reprint) AAAI 2026 Suppressing Final Layer Hidden State Jumps in Transformer Pretraining EACL 2026 Suspicious Alignment of SGD:A Fine-Grained Step Size Condition Analysis ALT 2026 TAPO: Dynamic Teacher and Perturbed Answer Injection for Policy Optimization AAAI 2026 The PID Controller Strikes Back: Classical Controller Helps Mitigate Barren Plateaus in Noisy Variational Quantum Circuits L4DC 2026 The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms AAAI 2026 Time-Frequency Token Advantage Clipping for Training Efficient Large Reasoning Model AAAI 2026 TIV: Thought Injection via Vectors for Efficient Reasoning in Large Reasoning Models AAAI 2026 Transformer with Controlled Attention for Synchronous Motion Captioning AAAI 2026