arXiv:2609.13739v1 Announce Type: cross Abstract: Language-model agents are increasingly deployed through diverse harnesses that differ in system prompts,…
PolicyMem: Geometric Policy Memory for LLM Governance
arXiv:2609.13734v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in real-world high-stakes applications,…
On the Equivalence of Stochastic Control and Path Space Formulations for Schr\”odinger Bridges over Compact Connected Lie Groups
arXiv:2609.13758v1 Announce Type: cross Abstract: We establish the equivalence between the stochastic optimal control and path space formulations of the…
AI News Brief Hourly Summary 2026-09-16 03h : 12 posts
12 posts published in the last hour 00:32Gap Entropy and Almost Instance-Wise Optimal Best-Arm Identification 00:32LayerRoute: Adaptive Layer-Skipping with LoRA-Preserved Quality for Efficient LLM Inference 00:32FaithfulBench: Does AI Counsel Uphold or Undermine the User’s Professed Faith? 00:32Leakage-Safe and Scheduler-Aware Machine…
Gap Entropy and Almost Instance-Wise Optimal Best-Arm Identification
arXiv:2609.13703v1 Announce Type: cross Abstract: In the best-arm identification problem, we are given $n$ stochastic arms with unknown means and wish to…
LayerRoute: Adaptive Layer-Skipping with LoRA-Preserved Quality for Efficient LLM Inference
arXiv:2609.13682v1 Announce Type: cross Abstract: We introduce LayerRoute, a parameter-efficient method for adaptive transformer layer-skipping that…
FaithfulBench: Does AI Counsel Uphold or Undermine the User’s Professed Faith?
arXiv:2609.13634v1 Announce Type: cross Abstract: Do AI assistants help believers reason about moral dilemmas consistently with their faith? We present…
Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction
arXiv:2609.13701v1 Announce Type: cross Abstract: Accurate job runtime prediction can improve scheduling-aware resource management in grid and distributed…
We don’t need AI regulation — leave safety to us, Nvidia’s Jensen Huang says
AI isn’t some kind of new form of “alien mind,” according to Jensen Huang. It’s just hardware and software, so safety can be engineered by each AI product…
Not all Negation Cues are Equal: Affixal Negations Yield Better Negation Understanding
arXiv:2609.13685v1 Announce Type: cross Abstract: Negation remains a longstanding challenge for both language models (LMs) and large language models…
Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repeated Runs
arXiv:2609.13582v1 Announce Type: cross Abstract: A clinical agent benchmark can report the same verdict on identical inputs while the agent files a…
mKernel: Fast Multi-GPU, Multi-Node Fused Kernels
arXiv:2609.13585v1 Announce Type: cross Abstract: Communication has become a bottleneck in distributed training and inference of large models. Overlapping…
Predictive audio representations for early detection and tracking of hidden dynamic objects
arXiv:2609.13595v1 Announce Type: cross Abstract: Predicting potential dangers is core to safety. Forecasting the presence of other traffic agents is core…
Domain-Specific Jargon in Large Language Models: A Comparative Analysis between General-Purpose and Specialist Models
arXiv:2609.13556v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown remarkable proficiency on general-purpose tasks, yet their…
An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS
arXiv:2609.13624v1 Announce Type: cross Abstract: Large Language Models (LLMs) are powerful zero-shot learners but remain prone to misalignment with human…
AI News Brief Hourly Summary 2026-09-16 02h : 11 posts
11 posts published in the last hour 23:32Attention Is All You Need (to Avoid Spurious Oscillations) 23:32Positive Topology and Feasible Refinement: Forcing Matrices, Positivity, and Information 23:32Rolling Day-Wise Mortality Prediction in Critically Ill Patients With AKI on CRRT Utilizing Machine…
Attention Is All You Need (to Avoid Spurious Oscillations)
arXiv:2609.13531v1 Announce Type: cross Abstract: Can attention move a shock across several cells in one update without breaking it? We develop a…
Positive Topology and Feasible Refinement: Forcing Matrices, Positivity, and Information
arXiv:2609.13523v1 Announce Type: cross Abstract: We develop a conceptual and operational account of Positive Topology starting from a basic relation…