← Techniques
Deep Learning › Techniques ›

Model Architecture

4351 directly classified papers

Papers per year

Papers

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025
Retrofitting Large Language Models with Dynamic Tokenization ACL 2025
Adaptive Rectangular Convolution for Remote Sensing Pansharpening CVPR 2025
Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need CVPR 2025
Bidirectional Human–AI Collaboration for Equitable Student Performance Prediction via Deep Uncertainty Learning IJCAI 2025
Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach CVPR 2025
Integral Transformer: Denoising Attention, Not Too Much Not Too Little EMNLP 2025
Superpose Task-specific Features for Model Merging EMNLP 2025
M-Wanda: Improving One-Shot Pruning for Multilingual LLMs EMNLP 2025
Multi-Frequency Contrastive Decoding: Alleviating Hallucinations for Large Vision-Language Models EMNLP 2025
Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling CVPR 2025
Context-aware Biases for Length Extrapolation EMNLP 2025
Attention to the Burstiness in Visual Prompt Tuning! ICCV 2025
LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling EMNLP 2025
How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation EMNLP 2025
Mechanistic Fine-tuning for In-context Learning EMNLP 2025
TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba ICCV 2025
Grouped Speculative Decoding for Autoregressive Image Generation ICCV 2025
Cognitive Fluctuations Enhanced Attention Network for Knowledge Tracing AAAI 2025
Improve Representation for Imbalanced Regression through Geometric Constraints CVPR 2025
Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing CVPR 2025
EntropyMark: Towards More Harmless Backdoor Watermark via Entropy-based Constraint for Open-source Dataset Copyright Protection CVPR 2025
DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis CVPR 2025
CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging CVPR 2025
RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style Guidance AAAI 2025