Transformers

SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization ICML 2025 SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining CVPR 2025 SalM²: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention AAAI 2025 SAM 2: Segment Anything in Images and Videos ICLR 2025 SAM4D: Segment Anything in Camera and LiDAR Streams ICCV 2025 Samba: A Unified Mamba-based Framework for General Salient Object Detection CVPR 2025 Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking ICLR 2025 SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation ICLR 2025 SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer ICML 2025 SAND: Enhancing Open-Set Neuron Descriptions through Spatial Awareness WACV 2025 Sandhi Splitting in Tamil and Telugu: A Sequence-to-Sequence Approach Leveraging Transformer Models COLING 2025 SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers CVPR 2025 SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens CVPR 2025 SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders ICCV 2025 ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimization MLHC 2025 Scalable Equilibrium Sampling with Sequential Boltzmann Generators ICML 2025 Scalable Vision Language Model Training via High Quality Data Curation ACL 2025 Scaling Action Detection: AdaTAD++ with Transformer-Enhanced Temporal-Spatial Adaptation ICCV 2025 Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks ICML 2025 Scaling Effects on Latent Representation Edits in GPT Models (Student Abstract) AAAI 2025 Scaling Graph-Based Dependency Parsing with Arc Vectorization and Attention-Based Refinement NAACL 2025 Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens ICLR 2025 Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More ICML 2025 Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study ICLR 2025 Scaling Transformer-Based Novel View Synthesis with Models Token Disentanglement and Synthetic Data ICCV 2025