#Computational efficiency
Latest news articles tagged with "Computational efficiency". Follow the timeline of events, related topics, and entities.
Articles (10)
-
🇺🇸 KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
[USA]
arXiv:2602.20217v1 Announce Type: cross Abstract: Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on s...
Related: #AI acceleration, #Model optimization, #Hardware adaptation -
🇺🇸 XMorph: Explainable Brain Tumor Analysis Via LLM-Assisted Hybrid Deep Intelligence
[USA]
arXiv:2602.21178v1 Announce Type: cross Abstract: Deep learning has significantly advanced automated brain tumor diagnosis, yet clinical adoption remains limited by interpretability and computational...
Related: #Medical AI, #Explainable AI, #Brain tumor diagnosis -
🇺🇸 Position: Why a Dynamical Systems Perspective is Needed to Advance Time Series Modeling
[USA]
arXiv:2602.16864v1 Announce Type: cross Abstract: Time series (TS) modeling has come a long way from early statistical, mainly linear, approaches to the current trend in TS foundation models. With a ...
Related: #Time‑series modelling, #Dynamical systems theory, #Machine learning and AI, #Model reconstruction -
🇺🇸 Random Wavelet Features for Graph Kernel Machines
[USA]
arXiv:2602.15711v1 Announce Type: cross Abstract: Node embeddings map graph vertices into low-dimensional Euclidean spaces while preserving structural information. They are central to tasks such as n...
Related: #Graph machine learning, #Node embeddings, #Graph kernels -
🇺🇸 PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
[USA]
arXiv:2601.18608v2 Announce Type: replace Abstract: Shapley values have emerged as a central game-theoretic tool in explainable AI (XAI). However, computing Shapley values exactly requires $2^d$ game...
Related: #Explainable AI, #Game‑theoretic feature attribution, #Machine‑learning interpretability, #Feature interactions -
🇺🇸 Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models
[USA]
arXiv:2602.12618v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pr...
Related: #Multimodal AI, #Model optimization -
🇺🇸 CoPE-VideoLM: Codec Primitives For Efficient Video Language Models
[USA]
arXiv:2602.13191v1 Announce Type: cross Abstract: Video Language Models (VideoLMs) empower AI systems to understand temporal dynamics in videos. To fit to the maximum context window constraint, curre...
Related: #Video AI, #Temporal processing -
🇺🇸 CATP: Cross-Attention Token Pruning for Accuracy Preserved Multimodal Model Inference
[USA]
arXiv:2404.08567v2 Announce Type: replace-cross Abstract: In response to the rising interest in large multimodal models, we introduce Cross-Attention Token Pruning (CATP), a precision-focused token p...
Related: #AI optimization, #Multimodal processing -
🇺🇸 MASPRM: Multi-Agent System Process Reward Model
[USA]
arXiv:2510.24803v2 Announce Type: replace-cross Abstract: Practical deployment of multi-agent systems (MAS) demands strong performance at test time, motivating methods that guide search during infere...
Related: #Multi-agent systems, #AI optimization -
🇺🇸 Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows
[USA]
arXiv:2509.11079v5 Announce Type: replace Abstract: Large Language Model (LLM)-based agentic systems have shown strong capabilities across various tasks. However, existing multi-agent frameworks ofte...
Related: #AI optimization, #Multi-agent systems