AI/ML arXiv cs.AI

A Variational Framework for LLM Generator-Regulator Games

Develops a variational framework for generator-regulator games to manage regulated language generation, such as censorship and phishing defense.

Other Hacker News

The Forge We Deserve

A discussion about 'The Forge We Deserve', likely referring to a development platform or toolset.

Other Hacker News

The 2-Year Apartment Rule

A discussion regarding a '2-Year Apartment Rule', which appears to be non-technical life advice or social commentary.

Other Hacker News

War Books: The Marine Corps Commandant's 2026 Reading List

A reading list for the Marine Corps Commandant for 2026, focused on war books.

Hardware/Chips Hacker News

AMD silently removes memory encryption from consumer Ryzen CPUs

AMD has quietly removed memory encryption features from its consumer-grade Ryzen CPUs.

Other Hacker News

I need your clothes, your boots, and your motorcycle

A post with a quote from a movie or story ('I need your clothes...'), appearing to be off-topic content.

Other Hacker News

About ASCII art and Jgs font (2023)

An exploration of ASCII art and the Jgs font from 2023.

AI/ML arXiv cs.AI

ASTRA: A Scalable Next-Generation ATCO Training Simulator with Autonomous Simpilots

ASTRA is a scalable ATCO training simulator that uses fine-tuned ASR and AI to automate simpilot roles and evaluate trainee performance.

AI/ML arXiv cs.AI

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Researchers demonstrate that Sparse Autoencoder (SAE) interventions to suppress harmful model behavior can be bypassed through residual-space optimization.

AI/ML arXiv cs.AI

Why SWAVE May Not Be All You Need:A Concept-Evolution Retrospective on Complex-Valued Recurrent Language Models

A retrospective on SWave, a complex-valued recurrent language model, detailing architectural failures like cos-domination collapse and subsequent fixes.

Cybersecurity arXiv cs.AI

Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response

Agentra is a multi-agent framework for enterprise intrusion response that converts alerts into structured plans grounded in MITRE and NIST standards.

Software Engineering Hacker News

Sogen – High-performance Windows and Linux userspace emulator

Sogen is a high-performance userspace emulator designed for both Windows and Linux environments.

Other Ars Technica

Hulk, Punisher join Peter Parker in Spider-Man: Brand New Day trailer

A new trailer for the Spider-Man: Brand New Day game has been released, featuring Hulk and Punisher.

AI/ML arXiv cs.AI

Vibe Coding Ate My Homework: An evaluation of AI approaches to greenfield software engineering and programming

Researchers evaluate 'vibe coding,' a paradigm where natural language prompts replace traditional code syntax for greenfield software engineering.

AI/ML arXiv cs.AI

A Link between Shock-wave Theory and Symmetry-reduced Stochastic Gradient Descent for Artificial Neural Networks

This paper establishes a mathematical link between shock-wave theory and symmetry-reduced stochastic gradient descent in artificial neural networks.

AI/ML arXiv cs.AI

Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression

A new structural pruning framework for Mixture-of-Experts (MoE) models improves compression and memory footprint without significant accuracy loss.

AI/ML arXiv cs.AI

DRIFT: Refining Instruction Data via On-Policy Data Attribution

DRIFT is a data refinement method for SFT that uses on-policy rollouts to improve the performance ceiling of LLMs.

AI/ML arXiv cs.AI

TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning

TRIDENT is a MARL framework designed for provably safe coordination in networked cyber-physical systems with hybrid actions and physics-governed dynamics.

AI/ML arXiv cs.AI

SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector

SAGE is a post-hoc sanitization method that reduces the trade-off between unlearning undesirable knowledge and preserving useful capabilities in LLMs.

Cybersecurity arXiv cs.AI

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems

CAREATTACK introduces a model-centric retriever attack framework for injecting malicious knowledge into RAG systems via retriever editing.