Infrastructure & Hardware B

Showing 91–120 of 203
  • arXiv cs.AI (Artificial Intelligence) · EN Infrastructure & Hardware
    ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs
    Retrieval-Augmented Generation (RAG) Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Inference & Efficiency
    Information Bottleneck Learning for Faithful Time Series Forecasting Explanations
    Inference Reinforcement Learning
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN Inference & Efficiency
    From Expert Reduction to Behavioral Divergence: Tracing Numerical State through Sparse MoE Inference
    DeepSeek Inference Mixture of Experts (MoE) Reinforcement Learning from Human Feedback (RLHF)
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.CL (Computation and Language) · EN Infrastructure & Hardware
    GGC: Selective Query Correction for Reliable Text-to-SPARQL Generation
    Inference Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.LG (Machine Learning) · EN New Model Releases
    GVR-Coder: A Visual-Feedback Framework for Structured SVG Generation in Complex Document and Meeting Scenarios
    Fine-tuning Reinforcement Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.LG (Machine Learning) · EN Inference & Efficiency
    A Query-Efficient Stochastic Volume Rendering Framework for Time-Varying Implicit Neural Volumes
    Inference
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.LG (Machine Learning) · EN Infrastructure & Hardware
    Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework
    Reinforcement Learning Transformer
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.LG (Machine Learning) · EN New Model Releases
    Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks
    Inference Neural Network
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.LG (Machine Learning) · EN Inference & Efficiency
    Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness
    Neural Network Quantization Transformer
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.LG (Machine Learning) · EN Infrastructure & Hardware
    What Makes Graph Unified? Principles and Generative Sliding-Window Transformer for Graph Foundation Models
    Transformer
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.CL (Computation and Language) · EN Infrastructure & Hardware
    SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions
    Meta Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    IFHierBench: Hierarchical Instruction Following for Large Language Models
    Deep Learning Machine Learning Neural Network Reinforcement Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
    AI Agents Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Infrastructure & Hardware
    Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning
    Inference Llama
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Inference & Efficiency
    A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding
    Inference
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Recall Before You Rank: Similarity-Guided Top-$K$ Reuse for Efficient Long-Context Attention
    Reinforcement Learning
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN Training & Fine-tuning
    Tight Sample Complexity for Low-Rank Adaptation: Matching Bounds and Rank Selection
    Deep Learning Fine-tuning Machine Learning Software Engineering
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • arXiv cs.CL (Computation and Language) · EN New Model Releases
    Looped Transformers with Source-Centered State Evolution
    Transformer
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • The Register (Data Centre) · EN Infrastructure & Hardware extract
    Qualcomm won’t be a big datacenter player anytime soon
    Qualcomm won't be a big data center player soon—but AI arrives just in time
    Qualcomm is unlikely to become a major data center player anytime soon, The Register reported. Still, the piece argues the AI boom arrived just in time for the chipmaker to offset the loss of Apple's business, giving it a timely new avenue for growth.
    Read original (The Register (Data Centre)) ↗
  • arXiv cs.CL (Computation and Language) · EN Inference & Efficiency
    Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories
    Inference Neural Network
    Read original (arXiv cs.CL (Computation and Language)) ↗
  • OpenAI Blog · EN Infrastructure & Hardware extract
    How avatarin built a 24/7 retail agent with GPT-Realtime
    avatarin builds 24/7 multilingual retail agent with GPT-Realtime
    GPT OpenAI
    avatarin used OpenAI's GPT-Realtime to give Yamada Denki shoppers 24/7 multilingual support through a conversational retail agent. Within two weeks it reportedly served around 30,000 users, showcasing a real-world deployment of real-time voice AI in retail.
    Read original (OpenAI Blog) ↗
  • Apple Machine Learning Research · EN Infrastructure & Hardware extract
    MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization
    Apple proposes MoMo for robot manipulation via spatiotemporal action tokens
    Transformer
    Apple researchers proposed MoMo, a robot-manipulation method that dials a motion mode using spatiotemporal action tokenization. The approach aims to let robots perform manipulation tasks accurately across diverse contexts by tokenizing actions over space and time.
    Read original (Apple Machine Learning Research) ↗
  • ITmedia AI+ · JA Infrastructure & Hardware extract
    AI・半導体企業トップが語る“稼ぎ頭”　キオクシア、フジクラ、東京エレデバの見解まとめ【無料PDF】
    ITmedia bundles top execs' AI-chip market outlook into a free PDF
    ITmedia offers a free PDF compiling how senior executives at Kioxia, Fujikura, Tokyo Electron Device and other firms view the volatile AI/semiconductor market and their key profit drivers. Specifics are left to the PDF itself and unconfirmed here.
    Read original (ITmedia AI+) ↗
  • arXiv cs.LG (Machine Learning) · EN Infrastructure & Hardware
    From Classification to Regression: Using a Fruitfly to Solve Equations
    Embeddings Inference Retrieval-Augmented Generation (RAG)
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Agents & Tool Use
    Can AI agents conduct open-ended AI research? Early evidence from two case studies
    AI Agents Reinforcement Learning Software Engineering
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • arXiv cs.LG (Machine Learning) · EN Infrastructure & Hardware
    Investigating reservoir computing for branch predictionin pipelined processors using emerging CMOS memristor devices
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.AI (Artificial Intelligence) · EN Infrastructure & Hardware
    Linguistic Monoculture in LLM-Assisted Language Use
    Read original (arXiv cs.AI (Artificial Intelligence)) ↗
  • NVIDIA Developer Blog · EN Agents & Tool Use extract
    How to Self-Host a Validated AI Coding Assistant with NVIDIA NeMo Guardrails
    NVIDIA: self-host a validated AI coding assistant via NeMo Guardrails
    AI Agents Generative AI NVIDIA
    An NVIDIA developer-blog post on self-hosting a validated AI coding assistant using NeMo Guardrails, framed around agent operation, infrastructure and safety. Note: the raw excerpt was blocked by a content guard, so specific components, supported models and guardrail rules are inferred from the title and URL and remain unverified from the body.
    Read original (NVIDIA Developer Blog) ↗
  • arXiv cs.LG (Machine Learning) · EN Infrastructure & Hardware
    Field Codes for Distributed Coupling Samplers and Certified Empirical Transport
    Embeddings
    Read original (arXiv cs.LG (Machine Learning)) ↗
  • arXiv cs.LG (Machine Learning) · EN Infrastructure & Hardware
    TreeCCA: Canonical Correlation Analysis via Gradient-Boosted Trees
    Machine Learning
    Read original (arXiv cs.LG (Machine Learning)) ↗