feed-forward network

Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis ACL 2026 Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring ACL 2026 DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models ACL 2026 Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow CVPR 2026 Efficiently Reconstructing Dynamic Scenes One D4RT at a Time CVPR 2026 Efficient Segmentation with Multimodal Large Language Model via Token Routing AAAI 2026 Global Structure-from-Motion Meets Feedforward Reconstruction CVPR 2026 IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting CVPR 2026 Infinity-MoE: Generalizing Mixture of Experts to Infinite Experts EACL 2026 MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer CVPR 2026 Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image CVPR 2026 SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images AAAI 2026 TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation CVPR 2026 TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction CVPR 2026 Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models ACL 2025 Asymmetric Factorized Bilinear Operation for Vision Transformer ICLR 2025 BlockPruner: Fine-grained Pruning for Large Language Models ACL 2025 Decoupling Memories, Muting Neurons: Towards Practical Machine Unlearning for Large Language Models ACL 2025 DiffSkip: Differential Layer Skipping in Large Language Models ACL 2025 DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts ACL 2025 DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025 GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal Guidance AAAI 2025 Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution ICCV 2025 Handling Delay in Real-Time Reinforcement Learning ICLR 2025 Label Set Optimization via Activation Distribution Kurtosis for Zero-Shot Classification with Generative Models EMNLP 2025