Efficient Computing

DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration ACL 2025 DAPE V2: Process Attention Score as Feature Map for Length Extrapolation ACL 2025 DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models EMNLP 2025 Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal CVPR 2025 DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis CVPR 2025 DeepRTL2: A Versatile Model for RTL-Related Tasks ACL 2025 Demystifying Small Language Models for Edge Deployment ACL 2025 Design Principle Transfer in Neural Architecture Search via Large Language Models AAAI 2025 DiffSkip: Differential Layer Skipping in Large Language Models ACL 2025 DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention CVPR 2025 Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs ACL 2025 Divide and Orthogonalize: Efficient Continual Learning with Local Model Space Projection UAI 2025 DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables CVPR 2025 DocMamba: Efficient Document Pre-training with State Space Model AAAI 2025 Don’t Think It Twice: Exploit Shift Invariance for Efficient Online Streaming Inference of CNNs AAAI 2025 DVAGen: Dynamic Vocabulary Augmented Generation EMNLP 2025 DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models CVPR 2025 Dynamic Layer Gating for Speech Enhancement Interspeech 2025 Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models ICLR 2025 Dynamic Operator Optimization for Efficient Multi-Tenant LoRA Model Serving AAAI 2025 Dynamic Sparse Training of Diagonally Sparse Networks ICML 2025 Dynamic-Width Speculative Beam Decoding for LLM Inference AAAI 2025 E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning EMNLP 2025 E4: Energy-Efficient DNN Inference for Edge Video Analytics via Early Exiting and DVFS AAAI 2025 ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training EMNLP 2025