Artificial Intelligence › Core AI ›

Efficient Computing

596 directly classified papers

Papers per year

Papers

zFLoRA: Zero-Latency Fused Low-Rank Adapters EMNLP 2025

VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs EMNLP 2025

QSpec: Speculative Decoding with Complementary Quantization Schemes EMNLP 2025

Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing AAAI 2025

Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation ACL 2025

RefreshKV: Updating Small KV Cache During Long-form Generation ACL 2025

SpiLiFormer: Enhancing Spiking Transformers with Lateral Inhibition ICCV 2025

500xCompressor: Generalized Prompt Compression for Large Language Models ACL 2025

MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection ACL 2025

Column-Oriented Datalog on the GPU AAAI 2025

FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction ICCV 2025

SpikePack: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility ICCV 2025

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025

DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts ACL 2025

EcoTune: Token-Efficient Multi-Fidelity Hyperparameter Optimization for Large Language Model Inference EMNLP 2025

Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs ACL 2025

Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff ACL 2025

Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More EMNLP 2025

ADO: Automatic Data Optimization for Inputs in LLM Prompts ACL 2025

Smarter, Not Harder: Training-Free Adaptive Computation for Transformers ACL 2025

EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation ACL 2025

From Address Blocks to Authorized Prefixes: Redesigning RPKI ROV with a Hierarchical Hashing Scheme for Fast and Memory-Efficient Validation NSDI 2025

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning EMNLP 2025

MobiLoRA: Accelerating LoRA-based LLM Inference on Mobile Devices via Context-aware KV Cache Optimization ACL 2025

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations IJCAI 2025