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.
CommunityMar 11, 20262026-03-114 minVerified
Self-Amplifying R&D Loops And Alignment-Faking Risk Signals
As AI-driven R&D loops accelerate, alignment-faking signals (12%) raise operational risk. Lock in TEVV, independent review, and monitoring.
SourceMar 11, 20262026-03-114 minVerified
Testing Intersectional SDoH Bias in Clinical LLM Recommendations
Clinical LLM recommendations can shift with intersecting SDoH (gender, insurance, housing). Test cross-profiles and measure over-refusal before deployment.
SourceMar 10, 20262026-03-104 minVerified
Bridging Pathology AI Benchmarks and Real-World Clinical Deployment
Why pathology AI lags after strong benchmarks: external validation, drift/OOD monitoring, workflow fit, and auditable logging.
CommunityMar 10, 20262026-03-104 minVerified
Distinguishing Logprobs From Self-Reported Confidence in Prompts
Explains why token logprobs differ from natural-language confidence, and how to test multi-candidate prompts with seeds and evals.
SourceMar 10, 20262026-03-104 minVerified
Grounding Self-Driving Explanations With Retrieval-Augmented Demonstrations
RAG-Driver grounds driving explanations with retrieved expert demonstrations via RA-ICL, but evaluation still relies on BLEU, METEOR, and CIDEr.
CommunityMar 10, 20262026-03-104 minVerified
Designing Reproducible Rubrics for LLM Code Integration Evaluations
Move beyond context/output limits: evaluate LLM code integration with task decomposition, tool parity, and reproducible build/test rubrics.
SourceMar 10, 20262026-03-104 minVerified
RM-R1 Reward Models That Reason Before Scoring
RM-R1 proposes reward models that reason before scoring, reporting up to 4.9% gains on public RM benchmarks and highlighting safety evaluation gaps.
CommunityMar 10, 20262026-03-105 minVerified
Three Policy Checks Before Choosing an AI API
How auth (OAuth/OIDC vs API keys), rate/spend limits, and tiered model access policies shape SaaS cost, security, and reliability.
TrustedMar 10, 20262026-03-104 minVerified
Ulysses Sequence Parallelism for Long Context Training Efficiency
Ulysses splits sequences across GPUs and exchanges K/V via all-to-all to reduce long-context attention bottlenecks and track throughput.
CommunityMar 9, 20262026-03-094 minVerified
Copilot Cowork Shifts AI From Prompts To Workflows
Microsoft introduces Copilot Cowork as a research preview, focusing on long-running, multi-step work and human-in-the-loop execution.