Efficient Computing

HyPiDecoder: Hybrid Pixel Decoder for Efficient Segmentation and Detection ICCV 2025 IAM: Efficient Inference through Attention Mapping between Different-scale LLMs ACL 2025 ICP: Immediate Compensation Pruning for Mid-to-high Sparsity CVPR 2025 IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION ICLR 2025 IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method EMNLP 2025 Image and Video Tokenization with Binary Spherical Quantization ICLR 2025 Image Embedding Sampling Method for Diverse Captioning EMNLP 2025 Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching CVPR 2025 ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition AAAI 2025 ImageTra: Real-Time Translation for Texts in Image and Video IJCNLP 2025 IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-Resolution ICCV 2025 IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling ICML 2025 ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs ACL 2025 Importance-Based Token Merging for Efficient Image and Video Generation ICCV 2025 Improved Coresets for Vertical Federated Learning: Regularized Linear and Logistic Regressions ICML 2025 Improving Accuracy and Generalization for Efficient Visual Tracking WACV 2025 Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers ICML 2025 Improving Data Efficiency via Curating LLM-Driven Rating Systems ICLR 2025 Improving Efficiency in Large Language Models via Extendable Block Floating Point Representation ACL 2025 Improving LLM Video Understanding with 16 Frames Per Second ICML 2025 Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling WACV 2025 Improving the Efficiency of Visually Augmented Language Models COLING 2025 Improving the Scaling Laws of Synthetic Data with Deliberate Practice ICML 2025 Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency ICLR 2025 In Benchmarks We Trust ... Or Not? EMNLP 2025