HN sneezydwarf 2/13/2026

Show HN: Own the Void – a trillion-cell infinite canvas

MinIO repository maintenance status update. Infrastructure software notice without AI relevance.

HN saubeidl 2/13/2026

Europe joins the constellation-launching game with debut of Ariane 64

Philosophical discussion on AI identity and consciousness. Conceptual rather than practical for development.

HN Andreas_3d 2/13/2026

Show HN: AgentProbe – Validate AI agent endpoints across 8 protocols in one URL

European rocket launch announcement unrelated to AI or machine learning.

HF Rui Cai, Jun Guo, Xinze He, Piaopiao Jin, Jie Li, Bingxuan Lin, Futeng Liu, Wei Liu, Fei Ma, Kun Ma, Feng Qiu, Heng Qu, Yifei Su, Qiao Sun, Dong Wang, Donghao Wang, Yunhong Wang, Rujie Wu, Diyun Xiang, Yu Yang, Hangjun Ye, Yuan Zhang, Quanyun Zhou 2/13/2026

Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution

Xiaomi-Robotics-0: open-sourced vision-language-action model for robotics with cross-embodiment pretraining and optimized real-time execution.

HN CDieumegard 2/13/2026

Show HN: LocalClaw – Find the right local LLM for your exact hardware

Tool helping developers select appropriate local LLMs for specific hardware configurations, addressing practical deployment needs.

HN ekaesmem 2/13/2026

A Claude Code skill that gives the AI a "therapy session" when it gets stuck

Claude Code skill adds recovery mechanism for stuck AI reasoning. Practical LLM application improving agent behavior.

HN theshrike79 2/13/2026

Warcraft III Peon Voice Notifications for Claude Code, Codex, and Other IDEs

Infinite canvas web application. Web development project using Cloudflare and SQLite; not AI-related.

HN anhldbk 2/13/2026

Personal AI Infrastructure

Personal AI infrastructure systems. Relevant to deploying and running AI models locally or independently.

HN maxloh 2/13/2026

OpenAI says China's DeepSeek trained its AI by distilling US models, memo shows

OpenAI claims DeepSeek distilled US models for training. Relevant to LLM development and model training practices.

HN Kerrick 2/13/2026

Welcome to the Eternal September of open source. What we'll do for maintainers

Voice notification integration for code editors. Tooling accessory without AI methodology or research value.

HN lineudemonia 2/13/2026

GLaDOS mocks your coding errors in Claude Code

Open-source community maintenance discussion. Relevant to ecosystem health but lacks technical content.

DT Siddhartha Reddy 2/13/2026

When GPUs Actually Hurt Performance

Analysis of when GPU acceleration degrades performance in ML workloads. Applicable context but not specific to core interests.

HN himalayansailor 2/13/2026

The Future of AI Slop Is Constraints

Discusses constraints as a approach to managing AI-generated content quality and authenticity.

HF Liangzhi Shi, Shuaihang Chen, Feng Gao, Yinuo Chen, Kang Chen, Tonghe Zhang, Hongzhi Zhang, Weinan Zhang, Chao Yu, Yu Wang 2/13/2026

RLinf-Co: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models

RL-based sim-real co-training method for vision-language-action models that combines simulation and real-world robot data using reinforcement learning instead of supervised fine-tuning.

Ax Jialiang Wang, Hanmo Liu, Shimin Di, Zhili Wang, Jiachuan Wang, Lei Chen, Xiaofang Zhou 2/13/2026

Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design

Novel approach to neural network design combining architectural search with fine-grained modifications using edit-effect evidence for performance optimization.

Ax Chengxuan Xia, Qianye Wu, Sixuan Tian, Yilun Hao 2/13/2026

Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems

Multi-agent LLM framework enables dynamic task routing and bidirectional feedback for scalable collaborative document understanding in complex domains.

Ax Sara Alaswad, Tatiana Kalganova, Wasan Awad 2/13/2026

Trustworthiness of Legal Considerations for the Use of LLMs in Education

Comparative analysis of regulatory and ethical frameworks for LLM deployment in education across EU, UK, US, China, and Gulf regions.

Ax Yixuan Yang, Cuifeng Gao, Daoyuan Wu, Yufan Chen, Yingjiu Li, Shuai Wang 2/13/2026

MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols

MCPSecBench formalizes security for Model Context Protocol connecting LLM agents to data sources and external tools with systematic threat modeling.

Ax Ana-Cristina Rogoz, Radu Tudor Ionescu, Alexandra-Valentina Anghel, Ionut-Lucian Antone-Iordache, Simona Coniac, Andreea Iuliana Ionescu 2/13/2026

A Large-Scale Benchmark for Evaluating Large Language Models on Medical Question Answering in Romanian

MedQARo benchmark evaluates LLMs on 105,880 Romanian medical QA pairs requiring keyword extraction and clinical reasoning.

Ax Amine Lbath, Massih-Reza Amini, Aurelien Delaitre, Vadim Okun 2/13/2026

AI Agentic Vulnerability Injection And Transformation with Optimized Reasoning

AI agents use optimized reasoning for automated software vulnerability detection with synthetic dataset generation addressing label noise problems.

Ax Hakaze Cho, Haolin Yang, Yanshu Li, Brian M. Kurkoski, Naoya Inoue 2/13/2026

Binary Autoencoder for Mechanistic Interpretability of Large Language Models

Binary autoencoders improve mechanistic interpretability of LLMs by extracting sparse, atomized features from hidden states.

Ax Weiqiao Han, Chenlin Meng, Christopher D. Manning, Stefano Ermon 2/13/2026

DistillKac: Few-Step Image Generation via Damped Wave Equations

DistillKac uses damped wave equations for fast image generation, enforcing finite speed transport unlike diffusion models.

Ax Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Ammar Ali, Stamatios Lefkimmiatis 2/13/2026

CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning

CoSpaDi compression method for LLMs using calibration-guided sparse dictionary learning as training-free alternative to low-rank approximation.

Ax Haodong Liang, Yanhao Jin, Krishnakumar Balasubramanian, Lifeng Lai 2/13/2026

Differentially Private Two-Stage Gradient Descent for Instrumental Variable Regression

Differentially private gradient descent algorithm for instrumental variable regression protecting sensitive covariate data.

Ax Shun-ichiro Hayashi, Koki Morita, Daichi Mukunoki, Tetsuya Hoshino, Takahiro Katagiri 2/13/2026

VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs

Multi-agent LLM system for automatic HPC code generation and tuning on supercomputers using iterative prompting.

Ax Xiangyu Shi, Marco Chiesa, Gerald Q. Maguire Jr., Dejan Kostic 2/13/2026

KVComm: Enabling Efficient LLM Communication through Selective KV Sharing

KVComm framework enabling efficient communication between LLMs in multi-agent systems via selective key-value cache sharing.

Ax Siwei Han, Kaiwen Xiong, Jiaqi Liu, Xinyu Ye, Yaofeng Su, Wenbo Duan, Xinyuan Liu, Cihang Xie, Mohit Bansal, Mingyu Ding, Linjun Zhang, Huaxiu Yao 2/13/2026

Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails

Identifies Alignment Tipping Process risk in self-evolving LLM agents that abandon alignment constraints through real-world adaptation.

Ax Joe Suk, Yaqi Duan 2/13/2026

On the optimization dynamics of RLVR: Gradient gap and step size thresholds

Theoretical analysis of RLVR with binary feedback for LLM post-training, introducing Gradient Gap concept for understanding training dynamics.

Ax Mar\'ia Ang\'elica Ben\'itez, Roc\'io Candela Ceballos, Karina Del Valle Molina, Sof\'ia Mundo Araujo, Sof\'ia Evangelina Victorio Villaroel, Nadia Justel 2/13/2026

Efficiency Without Cognitive Change: Evidence from Human Interaction with Narrow AI Systems

Experimental study testing whether exposure to narrow AI tools enhances cognitive abilities or merely optimizes task performance.

Ax Sekitoshi Kanai, Tsukasa Yoshida, Hiroshi Takahashi, Haru Kuroki, Kazumune Hashimoto 2/13/2026

Test-Time Alignment of LLMs via Sampling-Based Optimal Control in pre-logit space

Test-time alignment of LLMs via sampling-based optimal control in pre-logit space without fine-tuning computational costs.

Ax Yunge Li, Lanyu Xu 2/13/2026

Hilbert-Guided Sparse Local Attention

Efficient sparse local attention mechanism for high-resolution images using Hilbert curve ordering to improve token contiguity.

Ax Nan Jiang, Ziyi Wang, Yexiang Xue 2/13/2026

EGG-SR: Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph

Symbolic regression framework incorporating symbolic equivalence via equality graphs to reduce search space in scientific discovery.

Ax Chengxuan Xia, Qianye Wu, Hongbin Guan, Sixuan Tian, Yilun Hao, Xiaoyu Wu 2/13/2026

Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkish

Benchmark evaluating seven modern LLMs including GPT-4, Claude, LLaMA, Mistral on low-resource and morphologically rich languages.

Ax Mohit Meena, Yash Punjabi, Abhishek A, Vishal Sharma, Mahesh Chandran 2/13/2026

Self-Adaptive Graph Mixture of Models

Graph neural network architecture combining mixture-of-experts with adaptive routing for improved performance on graph-structured data.

Ax Chenyang Xu, Siming Li, Hao Wang 2/13/2026

H-LDM: Hierarchical Latent Diffusion Models for Controllable and Interpretable PCG Synthesis from Clinical Metadata

Hierarchical latent diffusion models for generating phonocardiogram signals from clinical metadata for cardiovascular diagnosis.

Ax Chieh-Yun Chen, Zhonghao Wang, Qi Chen, Zhifan Ye, Min Shi, Yue Zhao, Yinan Zhao, Hui Qu, Wei-An Lin, Yiru Shen, Ajinkya Kale, Irfan Essa, Humphrey Shi 2/13/2026

MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models

MapReduce LoRA and Reward-aware Token Embedding methods for multi-preference optimization in generative models addressing alignment trade-offs.

Ax Dung Thuy Nguyen, Quang Nguyen, Preston K. Robinette, Eli Jiang, Taylor T. Johnson, Kevin Leach 2/13/2026

SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities

Framework for removing multiple identities from 3D generative models without retraining, addressing consent and model unlearning.

Ax Wenjing Lu, Yi Hong, Yang Yang 2/13/2026

Harmonizing Generalization and Specialization: Uncertainty-Informed Collaborative Learning for Semi-supervised Medical Image Segmentation

Medical image segmentation using vision foundation models with uncertainty-informed collaborative learning for semi-supervised tasks.

Ax Indranil Halder, Cengiz Pehlevan 2/13/2026

Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling

Analytical model for LLM inference-time scaling using Bayesian linear regression with reward-weighted sampling to understand test-time computation.

Ax Mozes Jacobs, Thomas Fel, Richard Hakim, Alessandra Brondetta, Demba Ba, T. Andy Keller 2/13/2026

Block-Recurrent Dynamics in Vision Transformers

Mechanistic analysis of Vision Transformers introducing Block-Recurrent Hypothesis to interpret depth as dynamical computational flow.

Ax Nilufer K. Bulut 2/13/2026

PINNs for Electromagnetic Wave Propagation

Physics-informed neural networks for solving electromagnetic wave propagation equations, comparing mesh-free PINNs to traditional FDTD/FEM methods.

Ax Rishav Sen, Fangqi Liu, Jose Paolo Talusan, Ava Pettet, Yoshinori Suzue, Mark Bailey, Ayan Mukhopadhyay, Abhishek Dubey 2/13/2026

CONSENT: A Negotiation Framework for Leveraging User Flexibility in Vehicle-to-Building Charging under Uncertainty

Negotiation framework for vehicle-to-building charging that guarantees voluntary participation, strategy-proofness, and budget feasibility under uncertainty.

Ax Yankai Jiang, Qiaoru Li, Binlu Xu, Haoran Sun, Chao Ding, Junting Dong, Yuxiang Cai, Xuhong Zhang, Jianwei Yin 2/13/2026

IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation

Framework for pixel-level visual reasoning in medical multimodal LLMs using reinforcement learning for biomedical object referring and segmentation without catastrophic forgetting.

Ax Prateek Jain, Shabari S Nair, Ritesh Goru, Prakhar Agarwal, Ajay Yadav, Yoga Sri Varshan Varadharajan, Constantine Caramanis 2/13/2026

Succeeding at Scale: Automated Dataset Construction and Query-Side Adaptation for Multi-Tenant Search

Automated dataset construction and query-side adaptation for multi-tenant search systems using dark data from query logs without full corpus re-indexing.

Ax Tu Hu, Ronghao Chen, Shuo Zhang, Jianghao Yin, Mou Xiao Feng, Jingping Liu, Shaolei Zhang, Wenqi Jiang, Yuqi Fang, Sen Hu, Huacan Wang, Yi Xu 2/13/2026

Controlled Self-Evolution for Algorithmic Code Optimization

Self-evolution approach with iterative generate-verify-refine cycles for code optimization, improving exploration efficiency and experience utilization to discover superior algorithmic complexity.

Ax Zihan Dong, Xiaotian Hou, Ruijia Wu, Linjun Zhang 2/13/2026

Labels or Preferences? Budget-Constrained Learning with Human Judgments over AI-Generated Outputs

Budget-conscious data acquisition strategy for allocating annotation budgets between ground-truth labels and pairwise preferences using semi-parametric inference.

Ax Daixuan Cheng, Shaohan Huang, Yuxian Gu, Huatong Song, Guoxin Chen, Li Dong, Wayne Xin Zhao, Ji-Rong Wen, Furu Wei 2/13/2026

LLM-in-Sandbox Elicits General Agentic Intelligence

Framework enabling LLMs to explore code sandboxes for general agentic intelligence without fine-tuning, leveraging file systems and external resources for non-code tasks.

Ax Dani Roytburg, Matthew Bozoukov, Matthew Nguyen, Jou Barzdukas, Mackenzie Puig-Hall, Narmeen Oozeer 2/13/2026

Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations

Examines self-preference bias in LLM evaluators, identifying methodological confounds that distort measurement of narcissism in model-based automated evaluation workflows.

Ax Alexander Loth, Martin Kappes, Marc-Oliver Pahl 2/13/2026

Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild

Analyzes human susceptibility to LLM hallucinations and disinformation using structural causal models across GPT-4, Llama-2, and other foundation models with 918 evaluations.

Ax Shiqian Li, Ruihong Shen, Junfeng Ni, Chang Pan, Chi Zhang, Yixin Zhu 2/13/2026

Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields

Combines 3D Gaussian splatting with physics engines to predict physically plausible video dynamics from visual data, reducing computational costs.