Transformers

Enhancing Noise Resilience in Face Clustering via Sparse Differential Transformer AAAI 2026 EnViT: Enhancing the Performance of Early-Exit Vision Transformers via Exit-Aware Structured Dropout-Enabled Self-Distillation AAAI 2026 EPIC: Explanation of Pretrained Image Classification Networks via Prototypes AAAI 2026 EPSegFZ: Efficient Point Cloud Semantic Segmentation for Few- and Zero-Shot Scenarios with Language Guidance AAAI 2026 ES4MLL at SemEval-2026 Task 2: Set Attention Aggregation and Recurrent Temporal Modeling for Longitudinal Affect Prediction SemEval 2026 Evaluating Humanlike Memory Effects in Transformers Using Item Recognition Tasks CoNLL 2026 Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models ACL 2026 Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation AAAI 2026 Exploring Reliable Spatiotemporal Dependencies for Efficient Visual Tracking AAAI 2026 Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark CVPR 2026 Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge AAAI 2026 F2SST: Frequency-to-Spatial Semantic Transfer for Few-Shot Image Classification AAAI 2026 Fair Facial Attribute Recognition via Group-Decoupled Vision Transformer with Mask-Guided Correlation Suppression AAAI 2026 FARMER: Flow AutoRegressive Transformer over Pixels CVPR 2026 FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training AAAI 2026 FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding WACV 2026 FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation WACV 2026 Feasibility-Aware Masked Transformer for the Pickup-and-Delivery Problem with Time Windows (Student Abstract) AAAI 2026 Feature-Aware One-Shot Federated Learning via Hierarchical Token Sequences AAAI 2026 Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections MIDL 2026 Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction CVPR 2026 FILTR: Extracting Topological Features from Pretrained 3D Models CVPR 2026 Finding Distributed Object-Centric Properties in Self-Supervised Transformers CVPR 2026 FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers CVPR 2026 FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation CVPR 2026