← Techniques
Deep Learning › Techniques ›

Model Architecture

4351 directly classified papers

Papers per year

Papers

Structural Deep Encoding for Table Question Answering ACL 2025
DASS: A Dual-Branch Attention-based Framework for Trajectory Similarity Learning with Spatial and Semantic Fusion IJCAI 2025
Bidirectional Human–AI Collaboration for Equitable Student Performance Prediction via Deep Uncertainty Learning IJCAI 2025
TokensGen: Harnessing Condensed Tokens for Long Video Generation ICCV 2025
GSDet: Gaussian Splatting for Oriented Object Detection IJCAI 2025
Embeddings for Numerical Features Using tanh Activation ACL 2025
Frequency-Aware Deep Depth from Focus IJCAI 2025
Activating Distributed Visual Region within LLMs for Efficient and Effective Vision-Language Training and Inference ACL 2025
Top-I2P: Explore Open-Domain Image-to-Point Cloud Registration Using Topology Relationship IJCAI 2025
Low-Rank Interconnected Adaptation across Layers ACL 2025
Global Information Compensation Network for Image Denoising IJCAI 2025
A Multi-view Fusion Approach for Enhancing Speech Signals via Short-time Fractional Fourier Transform IJCAI 2025
GraphLSS: Integrating Lexical, Structural, and Semantic Features for Long Document Extractive Summarization NAACL 2025
STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation ACL 2025
Label Drop for Multi-Aspect Relation Modeling in Universal Information Extraction NAACL 2025
FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video CVPR 2025
Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks ACL 2025
Task-driven Layerwise Additive Activation Intervention NAACL 2025
MoDE: Effective Multi-task Parameter Efficient Fine-Tuning with a Mixture of Dyadic Experts NAACL 2025
An Association-based Fusion Method for Speech Enhancement IJCAI 2025
Enhancing Transformers Through Conditioned Embedded Tokens ICCV 2025
Drift-Adapter: A Practical Approach to Near Zero-Downtime Embedding Model Upgrades in Vector Databases EMNLP 2025
Parameter-Efficient Fine-Tuning via Circular Convolution ACL 2025
Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs EMNLP 2025
FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging EMNLP 2025