≈ the.bay.news
  1. 571

    Constraining the Commit Boundary: A DIO/ODI-Informed Authorization Guardrail for Agentic Entity Resolution

  2. 572

    The Envelope Layer: An Underestimated Surface of LLM Agent Defense

  3. 573

    SecDMP: Provably Secure Data Memory-Dependent Prefetching (Extended Version)

  4. 574

    Penny for Your Prompts: A Measurement Study of Contextual Leakage in AI Chat Platforms

  5. 575

    When POST Becomes GET: Investigating HTTP Method Interchangeability and Its Security Implications

  6. 576

    Revisiting Privacy Risks in Quantized Deep Neural Networks

  7. 577

    Classical Verification of Quantum Computation Beyond the Polynomial Hierarchy

  8. 578

    PipeLink: Contract-Guided Linking of GPU Kernel Components

  9. 579

    TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving

  10. 580

    Request-Adaptive Execution for Efficient Hybrid LLM Inference

  11. 581

    EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning

  12. 582

    Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis

  13. 583

    Pushing Dexterity and Safety for In-Hand Object Pose Reaching That Works Remarkably Well

  14. 584

    Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

  15. 585

    When Should We Intervene at Test Time?

  16. 586

    The K-property of equilibrium states for systems with non-uniform structure

  17. 587

    A semigroup approach for rough partial differential equations with jumps

  18. 588

    Measure of Maximal Entropy for Geodesic Flows on Noncompact Manifolds of Nonpositive Curvature

  19. 589

    Multicritical pseudo-Siegel bounds and the optimality of the Brjuno condition for all neutral polynomials

  20. 590

    The Assouad Dimension of Graphs: An Affirmative Answer to Fraser's Question

  21. 591

    Minimal acceleration and the topology of premonotonic cocycles

  22. 592

    Escape of mass for finite-area hyperbolic surfaces

  23. 593

    Polynomial automorphisms of C^2 with the same equilibrium measure

  24. 594

    Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions

  25. 595

    What Improves During Pretraining? Tracking Knowledge Acquisition with Point-in-Time Models

  26. 596

    MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control

  27. 597

    Can LLMs Uncover Hidden Physical Laws through Free Exploration?

  28. 598

    KPPax: preprocess differentiable kinetic ODE for machine learning in atmospheric chemistry

  29. 599

    Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops

  30. 600

    ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning

more →