Model Architecture

MRT: Learning Compact Representations with Mixed RWKV-Transformer for Extreme Image Compression AAAI 2026 MULTIBENCH++: A Unified and Comprehensive Multimodal Fusion Benchmarking Across Specialized Domains AAAI 2026 NESTOR: A Nested MOE-based Neural Operator for Large-Scale PDE Pre-Training CVPR 2026 NeuPAN: Direct Point Robot Navigation with End-to-End Model-Based Learning (Abstract Reprint) AAAI 2026 Neural Video Compression with Reference Hierarchy AAAI 2026 Next Patch Prediction for AutoRegressive Visual Generation AAAI 2026 Nighttime Flare Removal via Wavelet-Guided and Gated-Enhanced Spatial-Frequency Fusion Network AAAI 2026 OmniEvent: Unified Event Representation Learning AAAI 2026 OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs AAAI 2026 OneSparse: A Unified Framework for Sparse Activation Layers in Vision Models CVPR 2026 On the Calibration of Image Semi-Supervised Learning Models AAAI 2026 On the Mathematical Relationship Between Layer Normalization and Dynamic Activation Functions EACL 2026 Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design ACL 2026 Optimization-Free Style Transfer for 3D Gaussian Splats WACV 2026 Optimizing LoRA Allocation of MoE with the Alignment of Topic Correlation AAAI 2026 Organ-Aware Routing Mixture-of-Retrieval Augmented Generation for Fetal Ultrasound Reporting AAAI 2026 Orthogonal Spatial-temporal Distributional Transfer for 4D Generation AAAI 2026 PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork AAAI 2026 Palimpsest: Reconciling the CISS Trilemma for Incremental Nuclei Segmentation AAAI 2026 Parameter-Efficient Adaptation of Self-Supervised Models for Arabic Speech Recognition EACL 2026 Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models AAAI 2026 PartialNet: Compute Less, Perform Better AAAI 2026 Pb4U-GNet: Resolution-Adaptive Garment Simulation via Propagation-before-Update Graph Network AAAI 2026 PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation AAAI 2026 PCFormer: Accelerating Privacy-preserving Transformer Inference by Partition and Combination AAAI 2026