Neural Network Optimization

Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering ACL 2025 iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use EMNLP 2025 ITP: Instance-Aware Test Pruning for Out-of-Distribution Detection AAAI 2025 KAN: Kolmogorov–Arnold Networks ICLR 2025 Kolmogorov-Arnold Transformer ICLR 2025 K-order Ranking Preference Optimization for Large Language Models ACL 2025 LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering ACL 2025 Lambda-Skip Connections: the architectural component that prevents Rank Collapse ICLR 2025 LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov Subspace ICLR 2025 Language Fusion for Parameter-Efficient Cross-lingual Transfer ACL 2025 Language Models Can Easily Learn to Reason from Demonstrations EMNLP 2025 Language Models “Grok” to Copy NAACL 2025 Large Language and Protein Assistant for Protein-Protein Interactions Prediction ACL 2025 Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility ICCV 2025 LASER: Attention with Exponential Transformation ICML 2025 Last-iterate Convergence of Shuffling Momentum Gradient Method under the Kurdyka-Lojasiewicz Inequality JMLR 2025 Layer Duplication in LLMs EMNLP 2025 Layer-wise Quantization for Quantized Optimistic Dual Averaging ICML 2025 LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics ICLR 2025 Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction ICML 2025 Learning Continually by Spectral Regularization ICLR 2025 Learning Dynamical Coupled Operator For High-dimensional Black-box Partial Differential Equations IJCAI 2025 Learning dynamics in linear recurrent neural networks ICML 2025 Learning Dynamics of Deep Matrix Factorization Beyond the Edge of Stability ICLR 2025 Learning from Streaming Video with Orthogonal Gradients CVPR 2025