arXiv:2610.40728v1 Announce Type: cross Abstract: Medium-voltage feeders have few real-time measurements, so distribution system state estimation (DSSE)…
Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
arXiv:2506.20856v1 Announce Type: cross Abstract: Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While…
PrivacyFlow: Privacy in AI Agents through Information Flow Analysis and Consequence-Aware Risk Management
arXiv:2610.40714v1 Announce Type: cross Abstract: Autonomous LLM agents executing multi-step workflows over personal data often misalign with user privacy…
CausalGrade: Evidence-Guided Causal Graph Scoring with Jev
arXiv:2610.40692v1 Announce Type: cross Abstract: Evaluating the structural quality of candidate causal graphs when the true causal structure is unknown…
Import AI 479: Spacewar; low-latency tasks versus LLMs; Genie 4
Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this,…
Characterizing LLM Agent Behaviors in Module Shadowing Environments
arXiv:2610.40716v1 Announce Type: cross Abstract: LLM agents operating in untrusted workspaces face the risk of untrusted code execution during routine…
One brutal Minecraft night scared 50 AI agents into inventing chicken handoff protocols, a Fertilizer Officer, and fishing shifts
In experiments by Y Combinator Labs and Olam Labs, OpenAI’s GPT-6.1 Sol model showed two very different sides. When 50 agents were tasked with peaceful…
Recycle only when you have to!
arXiv:2610.40665v1 Announce Type: cross Abstract: AlphaFold 3-like models (e.g., Boltz, Protenix, etc.) have pushed the frontier of protein binder design.…
AI News Brief Hourly Summary 2026-11-02 17h : 15 posts
15 posts published in the last hour 15:35CausalWAM: Learning the Causes of Actions in World Action Models 15:35Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention 15:35The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results 15:35ACCT: Asymmetric…
CausalWAM: Learning the Causes of Actions in World Action Models
arXiv:2610.42096v1 Announce Type: new Abstract: World action models (WAMs) learn latent variables from observations and use these to both predict the…
Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention
arXiv:2610.42147v1 Announce Type: new Abstract: Agentic workflows are increasingly shifting towards long-horizon tasks, such as open-ended scientific…
The Knowledge Layer Model (KLM): Evidence-Visible AI Output, Routing Diagnostics, and Negative Results
arXiv:2610.42066v1 Announce Type: new Abstract: AI answers require more than apparent correctness: reviewers need to inspect their recorded basis. We…
ACCT: Asymmetric Cross-LLM Context Transfer
arXiv:2610.42116v1 Announce Type: new Abstract: In real-world deployments, large language model (LLM) systems are increasingly evolving from single-model…
OpenAI Launches Grid Protectors Program for Compute Campuses
On November 2, 2026, OpenAI launched the Grid Protectors Program, a national effort to arrange for future compute campuses to reduce electricity demand…
Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learning
arXiv:2506.20651v1 Announce Type: cross Abstract: Recent work has shown that gradient updates in federated learning (FL) can unintentionally reveal…
Same Question, Different Answers: Auditing Persona-Dependent Variation in Six LLMs on Smoking-Cessation Advice
arXiv:2610.42039v1 Announce Type: new Abstract: Hundreds of millions of people now ask large language model (LLM) chatbots for health advice, which raises…
DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention
arXiv:2610.41994v1 Announce Type: new Abstract: Linear attention scales linearly with sequence length, but its finite-state memory can limit long-context…
Protecting Your Brand from AI Distortion Calls for a New Enterprise Discipline
AI-powered disinformation is a serious threat to brand reputations. Deliberate attacks are only part of the problem. AI systems can also misrepresent a…