SourceMar 27, 20262026-03-274 minVerified
How Mathematics Should Govern AI Use Now
Why mathematics must address AI through values, practice, teaching, technology, and ethics to protect autonomy.
SourceMar 27, 20262026-03-274 minVerified
Memory and Randomness Bottlenecks in Probabilistic Trustworthy AI
A unified view of probabilistic trustworthy AI: performance bottlenecks may lie in memory and random data movement, not just compute.
SourceMar 27, 20262026-03-274 minVerified
What Infant Vision Learning Suggests for AI Systems
How infant low-data visual learning links concepts, causality, and prediction to reshape AI vision and robotics design.
SourceMar 27, 20262026-03-275 minVerified
Wireless World Models for AI-Native 6G Networks
How wireless world models combine 3D geometry and wave propagation to improve real-world generalization in AI-native 6G.
SourceMar 26, 20262026-03-263 minVerified
Rethinking LLM Agents as Adaptive Computation Graphs
View LLM agents as runtime-adaptive computation graphs to optimize accuracy, cost, latency, debugging, and control.
SourceMar 20, 20262026-03-205 minVerified
Judicial AI Depends on Human Algorithm Interaction Design
In courts, AI outcomes hinge less on model accuracy than on judge uptake, override patterns, accountability, and TEVV.
SourceMar 20, 20262026-03-203 minVerified
Medical AI Robotics Needs Governance Before Performance Claims
In medical AI robotics, governance, validation, and monitoring matter more than performance demos alone.
SourceMar 20, 20262026-03-204 minVerified
Tracing Long-Running Reasoning in Binary Analysis Agents
Examines why structured exploration and verifiable workflows may matter more than longer reasoning in LLM binary analysis.
SourceMar 18, 20262026-03-185 minVerified
Why Prediction-Equivalent Models Disagree on Feature Attribution
Models with identical predictions can still produce different feature attributions, challenging XAI reliability, audits, and governance.
SourceMar 18, 20262026-03-185 minVerified
Reasoning With AI, Not Letting It Decide Alone
How combining LLMs with computational argumentation could shift AI from making decisions for us to reasoning with us.
SourceMar 14, 20262026-03-144 minVerified
Educational AI Depends More on Design Than Models
A paper argues educational AI performance may depend less on model size and more on roles, skills, tools, runtime, and educator expertise.
SourceMar 13, 20262026-03-135 minVerified
Dynamic Coordination in Multi-Agent LLM and Robotics Systems
A minimal theory of multi-agent coordination through environmental memory, incentive fields, and feedback loops.
SourceMar 13, 20262026-03-135 minVerified
Stable Dependence Estimation for Autoencoder Feature Analysis
A new estimator for stable dependence analysis across autoencoder inputs, latents, and reconstructions, beyond mutual information pitfalls.
SourceMar 12, 20262026-03-125 minVerified
Active Provenance AIBOMs For Agentic AI Reproducibility And Security
Why SBOMs miss agentic AI runtime behavior, environment drift, and exploitability context—and how active provenance AIBOMs address it.
SourceMar 12, 20262026-03-124 minVerified
Adversarial Attacks on ML NIDS and Ensemble Defenses
ML-based NIDS can be evaded via adversarial examples like FGSM and GAN. Evaluate robustness and compare ensemble defenses.
SourceMar 12, 20262026-03-124 minVerified
How AI Co-Writing Shifts Writing And Opinions
AI co-writing can shift users from ideation to reactive selection, affecting expressed claims and even post-writing attitudes.
SourceMar 12, 20262026-03-124 minVerified
Epistemic Stability For Industrial LLM Hallucination Control
Industrial LLM hallucinations framed as a reproducibility problem, comparing five prompt strategies to reduce output variance across repeated runs.
SourceMar 12, 20262026-03-124 minVerified
Learning Quantum Probes for End-to-End RF Sensing
Reframes RF channels as sensors and jointly learns quantum probes with models under 5 ms/sample and pipeline constraints.
SourceMar 12, 20262026-03-123 minVerified
UniPINN Tackles Multifluid PINNs With Shared And Dynamic Learning
UniPINN targets three bottlenecks in multi-flow PINNs: shared vs specific features, negative transfer, and loss-scale imbalance.
SourceMar 11, 20262026-03-114 minVerified
Executable Skills Library for Self-Improving RL Agents
Defines skills as executable function code and manages them online via create-run-update-on-fail-save-on-success loops.
SourceMar 11, 20262026-03-113 minVerified
FuzzingRL Finds VLM Failures via Reinforcement Fine-Tuning
FuzzingRL combines fuzzing and reinforcement fine-tuning to automatically generate questions that induce VLM failures and reveal weak spots.
SourceMar 11, 20262026-03-114 minVerified
Markov Risk Surfaces And RL Search With LLM QA
Guardian turns messy case docs into schema-aligned spatiotemporal states, builds Markov risk surfaces, plans with RL, then validates via LLM QA.
SourceMar 11, 20262026-03-114 minVerified
Multi-LLM Consensus Workflow for Missing Child Investigations
Guardian proposes a multi-LLM pipeline with a consensus engine for early missing-child searches, emphasizing auditable TEVV operations.
SourceMar 11, 20262026-03-115 minVerified
Routing and Gating for Stable Online Continual Learning
In one-pass non-stationary streams, evaluate PEFT limits and use routing/gating plus stability budgets to reduce forgetting and latency.