model efficiency

3D Gaussian Point Encoders WACV 2026 A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification ACL 2026 AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization AAAI 2026 Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability AAAI 2026 Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models CVPR 2026 Efficient Vision Transformers via Token Merging with Head-wise Attention Correction WACV 2026 Evaluating Cost-Efficiency of LLMs in a RAG Setup on Polish Wikipedia: Quality vs. Energy Consumption EACL 2026 Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models AAAI 2026 GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search WACV 2026 Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding WACV 2026 Mobile-Oriented Video Diffusion: Enabling Text-to-Video Generation on Mobile Devices Without Retraining, Compression, or Pruning WACV 2026 Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models AAAI 2026 PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks CVPR 2026 SeqFeedNet: Sequential Feature Feedback Network for Background Subtraction WACV 2026 SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training WACV 2026 Token Pruning for Improving Graph-Generating State Space Model Performance EACL 2026 Achieving Speed-Accuracy Balance in Vision-based 3D Occupancy Prediction via Geometric-Semantic Disentanglement AAAI 2025 A Comprehensive Overhaul of Multimodal Assistant with Small Language Models AAAI 2025 Ada-K Routing: Boosting the Efficiency of MoE-based LLMs ICLR 2025 AdaV: Adaptive Text-visual Redirection for Vision-Language Models ACL 2025 Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency CVPR 2025 AMP-ViT: Optimizing Vision Transformer Efficiency with Adaptive Mixed-Precision Post-Training Quantization WACV 2025 An Efficient Hybrid Vision Transformer for TinyML Applications ICCV 2025 Assessing the Performance and Efficiency of Mamba ASR in Low-Resource Scenarios Interspeech 2025 Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression CVPR 2025