model efficiency

Matryoshka Multimodal Models ICLR 2025 Memory Efficient Matting with Adaptive Token Routing AAAI 2025 MixA: A Mixed Attention approach with Stable Lightweight Linear Attention to enhance Efficiency of Vision Transformers at the Edge ICCV 2025 MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices EMNLP 2025 Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning ICLR 2025 Numerical Pruning for Efficient Autoregressive Models AAAI 2025 OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models ICCV 2025 Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning ACL 2025 Partial Filter-Sharing: Improved Parameter-Sharing Method for Single Image Super-Resolution Networks WACV 2025 Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models ACL 2025 Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network AAAI 2025 Principles of Visual Tokens for Efficient Video Understanding ICCV 2025 QuantAttack: Exploiting Quantization Techniques to Attack Vision Transformers WACV 2025 RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone WACV 2025 ReGLA: Refining Gated Linear Attention NAACL 2025 Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions ICLR 2025 Router-Tuning: A Simple and Effective Approach for Dynamic Depth EMNLP 2025 Routing Experts: Learning to Route Dynamic Experts in Existing Multi-modal Large Language Models ICLR 2025 Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference ACL 2025 Smarter, Not Harder: Training-Free Adaptive Computation for Transformers ACL 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Streamlining Redundant Layers to Compress Large Language Models ICLR 2025 Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks ACL 2025 TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion CVPR 2025 Transformer Layers as Painters AAAI 2025