Transformers

Zero-Shot Styled Text Image Generation, but Make It Autoregressive CVPR 2025 ZIPA: A family of efficient models for multilingual phone recognition ACL 2025 ZipVL: Accelerating Vision-Language Models through Dynamic Token Sparsity ICCV 2025 $\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling NeurIPS 2024 $SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation NeurIPS 2024 NeuroPath: A Neural Pathway Transformer for Joining the Dots of Human Connectomes NeurIPS 2024 1024m at SMM4H 2024: Tasks 3, 5 & 6 - Self Reported Health Text Classification through Ensembles ACL 2024 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations CoRL 2024 3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection NeurIPS 2024 3D Geometric Shape Assembly via Efficient Point Cloud Matching ICML 2024 3D-LFM: Lifting Foundation Model CVPR 2024 A 2-Dimensional State Space Layer for Spatial Inductive Bias ICLR 2024 A3-108 Controlling Token Generation in Low Resource Machine Translation Systems EMNLP 2024 A Branching Decoder for Set Generation ICLR 2024 Abrupt Learning in Transformers: A Case Study on Matrix Completion NeurIPS 2024 Abstractive Multi-Video Captioning: Benchmark Dataset Construction and Extensive Evaluation COLING 2024 Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers ICLR 2024 Accelerating Augmentation Invariance Pretraining NeurIPS 2024 Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight NeurIPS 2024 Accelerating Transformer Pre-training with 2:4 Sparsity ICML 2024 Accelerating Transformers with Spectrum-Preserving Token Merging NeurIPS 2024 Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings EACL 2024 Accurate LoRA-Finetuning Quantization of LLMs via Information Retention ICML 2024 A Closer Look at Robustness of Vision Transformers to Backdoor Attacks WACV 2024 A Closer Look at the CLS Token for Cross-Domain Few-Shot Learning NeurIPS 2024