Efficient Computing

ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval ACL 2026 2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification CVPR 2025 3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding AAAI 2025 Accelerated Test-Time Scaling with Model-Free Speculative Sampling EMNLP 2025 Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence EMNLP 2025 Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps ACL 2025 Accelerating Cross-Encoders in Biomedical Entity Linking ACL 2025 Accelerating Dense LLMs via L0-regularized Mixture-of-Experts ACL 2025 Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling Interspeech 2025 Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR Interspeech 2025 Accurate KV Cache Quantization with Outlier Tokens Tracing ACL 2025 Activating Distributed Visual Region within LLMs for Efficient and Effective Vision-Language Training and Inference ACL 2025 AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction CVPR 2025 Adaptive Computation Modules: Granular Conditional Computation for Efficient Inference AAAI 2025 Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models AAAI 2025 AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference AAAI 2025 A Drop-In Solution for On-the-Fly Adaptation of Speculative Decoding in Large Language Models ACL 2025 Adversarial-Inspired Backdoor Defense via Bridging Backdoor and Adversarial Attacks AAAI 2025 A Lightweight Sparse Interaction Network for Time Series Forecasting AAAI 2025 AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models EMNLP 2025 An Efficient and Accurate Dynamic Sparse Training Framework Based on Parameter-Freezing AAAI 2025 APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs ACL 2025 Arctic-TILT. Business Document Understanding at Sub-Billion Scale ACL 2025 A Selective Re-learning Mechanism for Hyperspectral Fusion Imaging CVPR 2025 A Semantic-Aware Layer-Freezing Approach to Computation-Efficient Fine-Tuning of Language Models ACL 2025