Transformers

LA-MOTR: End-to-End Multi-Object Tracking by Learnable Association ICCV 2025 Language-Guided Hybrid Representation Learning for Visual Grounding on Remote Sensing Images IJCAI 2025 Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing EMNLP 2025 Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers EMNLP 2025 Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks AAAI 2025 Language models can learn implicit multi-hop reasoning, but only if they have lots of training data EMNLP 2025 Language Prompt for Autonomous Driving AAAI 2025 Language Repository for Long Video Understanding ACL 2025 Large Displacement Motion Transfer with Unsupervised Anytime Interpolation ICML 2025 LASER: An LLM-based ASR Scoring and Evaluation Rubric EMNLP 2025 Latent Action Pretraining from Videos ICLR 2025 Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation ICLR 2025 LaTeXMT: Machine Translation for LaTeX Documents EMNLP 2025 LAuReL: Learned Augmented Residual Layer ICML 2025 LaVin-DiT: Large Vision Diffusion Transformer CVPR 2025 LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling EMNLP 2025 LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation ICCV 2025 Layer Duplication in LLMs EMNLP 2025 Layered Insights: Generalizable Analysis of Human Authorial Style by Leveraging All Transformer Layers EMNLP 2025 LayerLock: Non-collapsing Representation Learning with Progressive Freezing ICCV 2025 LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer ICCV 2025 Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations EMNLP 2025 LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers AAAI 2025 LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians CVPR 2025 LeanK: Learnable K Cache Channel Pruning for Efficient Decoding EMNLP 2025