Neural Network Optimization

FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction ICCV 2025 Fast Quiet-STaR: Thinking Without Thought Tokens EMNLP 2025 Fast Training of Sinusoidal Neural Fields via Scaling Initialization ICLR 2025 Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks ICLR 2025 FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates ICML 2025 FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence ICML 2025 Find A Winning Sign: Sign Is All We Need to Win the Lottery ICLR 2025 Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic ICLR 2025 Fin-ExBERT: User Intent based Text Extraction in Financial Context using Graph-Augmented BERT and trainable Plugin EMNLP 2025 Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking ACL 2025 FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction EMNLP 2025 Flashback: Memory Mechanism for Enhancing Memory Efficiency and Speed in Deep Sequential Models COLING 2025 Flatness Improves Backbone Generalisation in Few-Shot Classification WACV 2025 Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks ICLR 2025 Flexible Tails for Normalizing Flows ICML 2025 Flexora: Flexible Low-Rank Adaptation for Large Language Models ACL 2025 Forecasting Continuous Non-Conservative Dynamical Systems in SO(3) ICCV 2025 Formation of Representations in Neural Networks ICLR 2025 Forward Knows Efficient Backward Path: Saliency-Guided Memory-Efficient Fine-tuning of Large Language Models ACL 2025 FractalLLM: Lossless Self-Speculative Decoding with Layer Embedded Self-Compression EMNLP 2025 FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecasting IJCAI 2025 FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures AAAI 2025 From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks ICLR 2025 From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers AAAI 2025 Frozen Language Models Are Gradient Coherence Rectifiers in Vision Transformers AAAI 2025