Efficient Computing

RECAST: Retrieval-Augmented Contextual ASR via Decoder-State Keyword Spotting EMNLP 2025 Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems? IJCNLP 2025 Rectifying Magnitude Neglect in Linear Attention ICCV 2025 Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering ICLR 2025 RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs ACL 2025 RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects CVPR 2025 ReFrame: Layer Caching for Accelerated Inference in Real-Time Rendering ICML 2025 RefreshKV: Updating Small KV Cache During Long-form Generation ACL 2025 RefVSR++: Exploiting Reference Inputs for Reference-Based Video Super-Resolution WACV 2025 Regional Distribution of the /el/-/æl/ Merger in Australian English COLING 2025 Regional-TinyStories: A Small Language Model Framework for Evaluating Language Learning, Tokenizers, and Datasets IJCNLP 2025 Region-based Content Enhancement for Efficient Video Analytics at the Edge NSDI 2025 ReGLA: Refining Gated Linear Attention NAACL 2025 Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems ICML 2025 RelationalCoder: Rethinking Complex Tables via Programmatic Relational Transformation ACL 2025 RelGNN: Composite Message Passing for Relational Deep Learning ICML 2025 Reliable and Cost-Effective Exploratory Data Analysis via Graph-Guided RAG EMNLP 2025 Reliable, Reproducible, and Really Fast Leaderboards with Evalica COLING 2025 Reliever: Relieving the Burden of Costly Model Fits for Changepoint Detection JMLR 2025 RemDet: Rethinking Efficient Model Design for UAV Object Detection AAAI 2025 Removing Cost Volumes from Optical Flow Estimators ICCV 2025 RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models EMNLP 2025 Representation Shift: Unifying Token Compression with FlashAttention ICCV 2025 ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation ICML 2025 Residual Diffusion Deblurring Model for Single Image Defocus Deblurring AAAI 2025