Transformers

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference ICML 2025 Sparse Activation Editing for Reliable Instruction Following in Narratives EMNLP 2025 Sparse Fine-Tuning of Transformers for Generative Tasks ICCV 2025 SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity ICML 2025 Sparse Rewards Can Self-Train Dialogue Agents ACL 2025 SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference ICCV 2025 Sparsifying Mamba EMNLP 2025 Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation ICCV 2025 SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks AAAI 2025 Spatiotemporal-Aware Neural Fields for Dynamic CT Reconstruction AAAI 2025 SPE Attention: Making Attention Equivariant to Semantic-Preserving Permutation for Code Processing EMNLP 2025 SpectFormer: Frequency and Attention is What You Need in a Vision Transformer WACV 2025 SpectralAR: Spectral Autoregressive Visual Generation ICCV 2025 Spectral Image Tokenizer ICCV 2025 Spectral Informed Mamba for Robust Point Cloud Processing CVPR 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Spectral State Space Model for Rotation-Invariant Visual Representation Learning CVPR 2025 Speech-Based Automatic Chronic Kidney Disease Diagnosis via Transformer Fusion of Glottal and Spectrogram Features Interspeech 2025 Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs EMNLP 2025 SpeechEE@XLLM25: End-to-End Structured Event Extraction from Speech ACL 2025 SpeechHGT: A Multimodal Hypergraph Transformer for Speech-Based Early Alzheimer’s Disease Detection IJCAI 2025 SpeechMLC: Speech Multi-label Classification Interspeech 2025 SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception CVPR 2025 Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation AAAI 2025 SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) Complexity ICML 2025