feed-forward network

Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory ACL 2025 LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates ACL 2025 Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats ICCV 2025 Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models ICML 2025 Mixture of Lookup Experts ICML 2025 No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views ICCV 2025 Olica: Efficient Structured Pruning of Large Language Models without Retraining ICML 2025 Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs ICLR 2025 Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries EMNLP 2025 RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs ACL 2025 SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression AAAI 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models ACL 2025 Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens EMNLP 2025 Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities ICML 2025 When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models EMNLP 2025 Accelerating Transformer Pre-training with 2:4 Sparsity ICML 2024 Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps ICLR 2024 BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts NeurIPS 2024 Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers NeurIPS 2024 Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation ICML 2024 CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification EMNLP 2024 Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning NeurIPS 2024 ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks NeurIPS 2024 Enhancing Parameter-efficient Fine-tuning with Simple Calibration Based on Stable Rank COLING 2024