Neural Network Optimization

Cautious Next Token Prediction ACL 2025 Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning JMLR 2025 CLaSp: In-Context Layer Skip for Self-Speculative Decoding ACL 2025 CodeAnubad at BLP-2025 Task 2: Efficient Bangla-to-Python Code Generation via Iterative LoRA Fine-Tuning of Gemma-2 AACL 2025 Collaborative Multi-LoRA Experts with Achievement-based Multi-Tasks Loss for Unified Multimodal Information Extraction IJCAI 2025 CoMMIT: Coordinated Multimodal Instruction Tuning EMNLP 2025 Complexity Experts are Task-Discriminative Learners for Any Image Restoration CVPR 2025 ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning ICLR 2025 Continual Gradient Low-Rank Projection Fine-Tuning for LLMs ACL 2025 Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models? ACL 2025 Continuum Attention for Neural Operators JMLR 2025 CoPINN: Cognitive Physics-Informed Neural Networks ICML 2025 CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter ACL 2025 COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025 CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference ICLR 2025 CoT-Valve: Length-Compressible Chain-of-Thought Tuning ACL 2025 Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent AAAI 2025 Covariance-Based Space Regularization for Few-Shot Class Incremental Learning WACV 2025 Credit-based self organizing maps: training deep topographic networks with minimal performance degradation ICLR 2025 Critical Influence of Overparameterization on Sharpness-aware Minimization UAI 2025 Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic ACL 2025 Cross-Task Affinity Learning for Multitask Dense Scene Predictions WACV 2025 CTBench: A Library and Benchmark for Certified Training ICML 2025 Curse of High Dimensionality Issue in Transformer for Long Context Modeling ICML 2025 Cut Your Losses in Large-Vocabulary Language Models ICLR 2025