Efficient Computing

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning AAAI 2025 Training compute-optimal transformer encoder models EMNLP 2025 Training-free and Adaptive Sparse Attention for Efficient Long Video Generation ICCV 2025 Training-Free and Hardware-Friendly Acceleration for Diffusion Models via Similarity-based Token Pruning AAAI 2025 Training LLMs with MXFP4 AISTATS 2025 Training Long-Context LLMs Efficiently via Chunk-wise Optimization ACL 2025 Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferral EMNLP 2025 Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling ACL 2025 Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking AAAI 2025 Ultra-Sparse Memory Network ICLR 2025 UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation ACL 2025 UniPCGC: Towards Practical Point Cloud Geometry Compression via an Efficient Unified Approach AAAI 2025 Unlocking the Power of LSTM for Long Term Time Series Forecasting AAAI 2025 Value Residual Learning ACL 2025 VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification CVPR 2025 VERSE: Verification-based Self-Play for Code Instructions AAAI 2025 Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models CVPR 2025 ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention AAAI 2025 VISTREAM: Improving Computation Efficiency of Visual Streaming Perception via Law-of-Charge-Conservation Inspired Spiking Neural Network CVPR 2025 VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service ACL 2025 VSSD: Vision Mamba with Non-Causal State Space Duality ICCV 2025 Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning EMNLP 2025 Weight-Aware Activation Sparsity with Constrained Bayesian Optimization Scheduling for Large Language Models EMNLP 2025 When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs EMNLP 2025 WISE: A Framework for Gigapixel Whole-Slide-Image Lossless Compression CVPR 2025