Efficient Computing

Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly EMNLP 2025 zFLoRA: Zero-Latency Fused Low-Rank Adapters EMNLP 2025 𝜙-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation ACL 2025 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos CVPR 2024 Accelerating Multilingual Language Model for Excessively Tokenized Languages ACL 2024 Accelerating Transformers with Spectrum-Preserving Token Merging NeurIPS 2024 A Cost-Efficient Modular Sieve for Extracting Product Information from Company Websites EMNLP 2024 Adaptive Depth Networks with Skippable Sub-Paths NeurIPS 2024 Advancing Parameter Efficiency in Fine-tuning via Representation Editing ACL 2024 ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers CVPR 2024 Alias-Free Mamba Neural Operator NeurIPS 2024 All Rivers Run to the Sea: Private Learning with Asymmetric Flows CVPR 2024 A Model for Estimating the Economic Costs of Computer Vision Systems That Use Deep Learning AAAI 2024 A Multi-Level Framework for Accelerating Training Transformer Models ICLR 2024 Anchor-based Large Language Models ACL 2024 An Empirical Study of Distributed Deep Learning Training on Edge (Student Abstract) AAAI 2024 An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference EMNLP 2024 Arbitrary-Scale Video Super-resolution Guided by Dynamic Context AAAI 2024 Archaeoscape: Bringing Aerial Laser Scanning Archaeology to the Deep Learning Era NeurIPS 2024 AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation NeurIPS 2024 A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression EMNLP 2024 AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising NeurIPS 2024 Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models CVPR 2024 BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model CVPR 2024 BASS: Batched Attention-optimized Speculative Sampling ACL 2024