model architecture

Enabling Autoregressive Models to Fill In Masked Tokens EACL 2026 LoResMT 2026 Shared Task System Description EACL 2026 lrnnx: A library for Linear RNNs EACL 2026 MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe CVPR 2026 Mix-QSAM2: Mixed-Precision Quantization for High Fidelity Segmentation in Resource Constrained Scenarios AAAI 2026 MULTIBENCH++: A Unified and Comprehensive Multimodal Fusion Benchmarking Across Specialized Domains AAAI 2026 PhysicsCorrect: A Training-Free Approach for Stable Neural PDE Simulations AAAI 2026 QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation WACV 2026 Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with Prompts AAAI 2026 Reviving ConvNeXt for Efficient Convolutional Diffusion Models CVPR 2026 Scalable Mixed-Integer Optimization with Neural Constraints via Dual Decomposition AAAI 2026 A Closer Look into Mixture-of-Experts in Large Language Models NAACL 2025 Adaptive Camera Sensor for Vision Models ICLR 2025 Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting AAAI 2025 An Analysis of Datasets, Metrics and Models in Keyphrase Generation ACL 2025 Bag of Tricks for Sparse Mixture-of-Experts: A Benchmark Across Reasoning, Efficiency, and Safety EMNLP 2025 Bandit Based Attention Mechanism in Vision Transformers WACV 2025 Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers WACV 2025 Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models CVPR 2025 Building Vision Models upon Heat Conduction CVPR 2025 Can Adversarial Examples Be Parsed to Reveal Victim Model Information? WACV 2025 CoMeDi Shared Task: Median Judgment Classification & Mean Disagreement Ranking with Ordinal Word-in-Context Judgments COLING 2025 Cost-Optimal Grouped-Query Attention for Long-Context Modeling EMNLP 2025 DCT-CryptoNets: Scaling Private Inference in the Frequency Domain ICLR 2025 Deconstructing Attention: Investigating Design Principles for Effective Language Modeling IJCNLP 2025