Skip to content
conftrace_

transformer architecture

1,645 papers

Explore in graph

Also known as

TA

Co-occurring keywords · papers mentioning both

attention mechanism (207) neural machine translation (122) multimodal learning (80) representation learning (78) language model (67) self-attention mechanism (66) transformer model (66) neural network (64) large language model (63) model compression (55)

Papers

Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models NAACL 2025 Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning NAACL 2025 Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking ACL 2025 InstructAny2Pix: Image Editing with Multi-Modal Prompts NAACL 2025 Integral Transformer: Denoising Attention, Not Too Much Not Too Little EMNLP 2025 Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive Segmentation ICCV 2025 InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling ICLR 2025 Intra and Inter Parser-Prompted Transformers for Effective Image Restoration AAAI 2025 Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation CVPR 2025 KeyPose: Category-Level 6D Object Pose Estimation with Self-Adaptive Keypoints AAAI 2025 KV Shifting Attention Enhances Language Modeling ICML 2025 Lambda-Skip Connections: the architectural component that prevents Rank Collapse ICLR 2025 Language Models Are Implicitly Continuous ICLR 2025 Layer Duplication in LLMs EMNLP 2025 Learning Efficient Positional Encodings with Graph Neural Networks ICLR 2025 Learning to Filter Outlier Edges in Global SfM CVPR 2025 Learning Transformer-based World Models with Contrastive Predictive Coding ICLR 2025 Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory ACL 2025 Less Is More: Token Context-Aware Learning for Object Tracking AAAI 2025 LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds ICCV 2025 Lidar Waveforms are Worth 40x128x33 Words ICCV 2025 LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph AAAI 2025 LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields CVPR 2025 LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers NAACL 2025 LoRACoE: Improving Large Language Model via Composition-based LoRA Expert EMNLP 2025