≈ the.bay.news
  1. 811

    HiLO: Towards Product-Level Graceful Degradation with a Quality-Aware, Load-Aware Control Framework

  2. 812

    When and Why to Use TMA: A Workload-Grounded Characterization of Tensor Memory Acceleration on NVIDIA Hopper GPUs

  3. 813

    FrontGI: Architecture-Aware Parallel GNN Inference on Chiplet-Based Multicore Systems

  4. 814

    Waypoint: Analytically Modeling GEMM for CPUs

  5. 815

    Priority-Aware Scheduler for Serverless Functions Provision and Load Balancing

  6. 816

    A JiT-Based Denoising Defense Method Against Adversarial Examples for Radio Signal Automatic Modulation Classification

  7. 817

    Uncertainty Evaluation to Support Safety of the Intended Functionality Analysis for Determining the Applicability of Performance Targets Across Triggering Conditions in ML-Based LiDAR Object Detection

  8. 818

    Spherical Brownian Diffusion for Language Modeling

  9. 819

    FlowGenesis: Representation-Driven Self-Organization of Neural Architectures

  10. 820

    A Diagnostic Protocol for GNNs in Electricity Load Forecasting: Separating Parameter Sharing from Neighborhood Access

  11. 821

    Toward Fast Human Reaction Modeling from High-Frequency Digital Interaction Data

  12. 822

    Zero-Shot Multi-Class Wafer Map Classification with Rule-Ordered Prompts for Large Multimodal Models

  13. 823

    Improving Instruction Hierarchy by Learning from Goal-Goal Conflicts

  14. 824

    Subspace Crystallization in Grokking: Rank Compression Tracks the Phase Transition

  15. 825

    UTA: Universal Training Adaptive Learning Rate Decay

  16. 826

    Generative AI in Turbulence: Foundations, Applications, Validations and Benchmarks

  17. 827

    Phantom Forgetting: How BatchNorm State Fakes Deletion in Edge Split Machine Unlearning

  18. 828

    Attack logics, not outputs: Concept-based Property Attacks for Shortcut Elimination in Neural Networks

  19. 829

    A Certified Robustness Framework for Backdoor Poisoning Attacks using $f$-Divergences

  20. 830

    Intellectual Property Protection of Hyperdimensional Computing Classifiers: Black-Box Ownership Verification via Model Watermarking

  21. 831

    The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming

  22. 832

    Steering for Safety, Hijacking for Profit: Trojan Threats in the LLM Activation Steering Supply Chain

  23. 833

    GuardRAG: A Post-Retrieval Defense against Poisoning Attacks in Retrieval-Augmented Generation

  24. 834

    CoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems

  25. 835

    Partial Modal Tensor Regression

  26. 836

    The Information Geometry of Representation Formation

  27. 837

    The Symmetry of Differential Neural Tangent Kernel under the Orthogonal Group

  28. 838

    TCSP3.0: Template-Based Crystal Structure Prediction with Coefficient-Preserving Element Substitution and Structural Diversity

  29. 839

    Zeptojoule Microwave Calorimetry with Nanosecond Recovery in Graphene

  30. 840

    Charge state and hydration of vacancies in silicon and silicon carbide in contact with water: A grand-canonical first-principles stability map

more →