Transformers

Learning Procedural-Aware Video Representations Through State-Grounded Hierarchy Unfolding AAAI 2026 Learning to Parse and Reconstruct: Bidirectional Modeling of Question-to-Program Mapping AAAI 2026 Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling CVPR 2026 Life, Machine Learning, and the Search for Habitability: Predicting Biosignature Fluxes for the Habitable Worlds Observatory AAAI 2026 Linguistic Profiling of Transformer Embedding Geometry CoNLL 2026 LitePT: Lighter Yet Stronger Point Transformer CVPR 2026 LiveGesture: Streamable Co-Speech Gesture Generation Model CVPR 2026 Lizard: An Efficient Linearization Framework for Large Language Models ACL 2026 LoGIC: Multi-LoRA Guided Importance Consensus for Multi-Task Pruning in Vision Transformers AAAI 2026 Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models AAAI 2026 LoGoSeg: Integrating Local and Global Features for Open-Vocabulary Semantic Segmentation AAAI 2026 LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs AAAI 2026 LongStream: Long-Sequence Streaming Autoregressive Visual Geometry CVPR 2026 MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation CVPR 2026 Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning AAAI 2026 Manipulating the Mind’s Eye: A-SAGE, the Attention-Based Attack on ViT Explainability AAAI 2026 MarkushGrapher-2: End-to-end Multimodal Recognition of Chemical Structures CVPR 2026 MaRS: A Multi-modality Very-high-resolution Remote Sensing Foundation Model with Cross-Granularity Meta-Modality Learning AAAI 2026 MaskDexGrasp: Generative Masked Modeling for Part-Aware Dexterous Grasp Synthesis CVPR 2026 Masked Clustering Prediction for Unsupervised Point Cloud Pre-training AAAI 2026 Matching Every Pair to Track Every Point: PairFormer for All-Pairs Tracking and Video Trajectory Fields CVPR 2026 MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers ACL 2026 MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling EACL 2026 MechaFormer: Sequence Learning for Kinematic Mechanism Design Automation AAAI 2026 Mechanistic Analysis Of Universality: Numerical Comparison Circuits Across Transformer Architectures ACL 2026