Model Architecture

SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation ICCV 2025 SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement ICLR 2025 SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model CVPR 2025 SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers ICLR 2025 Scalable Image Tokenization with Index Backpropagation Quantization ICCV 2025 Scalable Model Merging with Progressive Layer-wise Distillation ICML 2025 Scaling Action Detection: AdaTAD++ with Transformer-Enhanced Temporal-Spatial Adaptation ICCV 2025 Scaling Inference Time Compute for Diffusion Models CVPR 2025 Scaling Mesh Generation via Compressive Tokenization CVPR 2025 Scaling up the State Size of RNN LLMs for Long-Context Scenarios ACL 2025 SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming ICML 2025 Seamlessly Integrating Tree-Based Positional Embeddings into Transformer Models for Source Code Representation ACL 2025 Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors EMNLP 2025 Segment-Based Attention Masking for GPTs ACL 2025 Self-calibration for Language Model Quantization and Pruning NAACL 2025 Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis ICCV 2025 SEMU: Singular Value Decomposition for Efficient Machine Unlearning ICML 2025 SensorFlow: Sensor and Image Fused Video Stabilization WACV 2025 SEP: A General Lossless Compression Framework with Semantics Enhancement and Multi-Stream Pipelines IJCAI 2025 Separating the Wheat from the Chaff: Spatio-Temporal Transformer with View-interweaved Attention for Photon-Efficient Depth Sensing AAAI 2025 Sequence Accumulation and Beyond: Infinite Context Length on Single GPU and Large Clusters AAAI 2025 SerialGen: Personalized Image Generation by First Standardization Then Personalization CVPR 2025 SGD Jittering: A Training Strategy for Robust and Accurate Model-Based Architectures ICML 2025 Sharper and Faster mean Better: Towards More Efficient Vision-Language Model for Hour-scale Long Video Understanding ACL 2025 Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity EMNLP 2025