HN database64128 3/3/2026

Latest ToS update includes class action waiver and forced arbitration

Discussion of Terms of Service changes adding class action waiver and arbitration clauses to Zed editor.

HN human_hack3r 3/3/2026

Ask HN: How to get traction for Open-Source Projects

Community discussion asking for strategies to gain traction for open-source agentic AI infrastructure projects.

HN dheerajmp 3/3/2026

Building AI agent for our own company

Company built custom AI agent on LeanMCP platform in 2 hours that answers product documentation questions better than general-purpose LLMs.

HN luthor190397 3/3/2026

Show HN: Neural Siege – A Multi-Agent RL Combat Simulation

Open-source multi-agent reinforcement learning combat simulation with per-agent PPO training, checkpointing, and telemetry logging.

HN pollow 3/3/2026

Show HN: C-Suite Skills – a full exec team as skills

Claude Code skills pack providing AI-powered executive team roles (CEO, CFO, CMO, etc.) to assist solo founders with multi-domain decision-making.

HN Evan233 3/3/2026

Veo 3 AI

Google Veo 3 text-to-video generation model with improved motion, clarity, and realism compared to previous versions.

HN gauravvij137 3/3/2026

Show HN: GitHub Repo Agent – an agent that explores and reasons on GitHub repos

Agent that explores GitHub repositories, indexes codebases, and answers questions about code structure and dependencies using LLM reasoning.

HN monokist 3/3/2026

Strict Monospace Font for LLM-CLI user using Chinese Japanese Korean, CodexMono

CodexMono monospace font designed for strict fixed-width rendering with CJK character support in terminals.

Ax Sai Sandeep Damera, Ryan Matheu, Aniruddh G. Puranic, John S. Baras 3/3/2026

Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networks

Polynomial Surrogate Training for ternary logic gate networks: Method to extend differentiable logic networks to ternary Kleene logic with uncertainty handling.

Ax Zihan Wang, Yijun Dong, Qi Lei 3/3/2026

When does Chain-of-Thought Help: A Markovian Perspective

Theoretical analysis of when chain-of-thought prompting helps LLMs using Markov chain modeling to identify transition alignment as key factor.

Ax Ariel Lubonja, Jungsang Yoon, Haoyin Xu, Yue Wan, Yilin Xu, Richard Stotz, Mathieu Guillame-Bert, Joshua T. Vogelstein, Randal Burns 3/3/2026

Vectorized Adaptive Histograms for Sparse Oblique Forests

Vectorized Adaptive Histograms for Sparse Oblique Forests: Method to optimize histogram and sorting tradeoffs in random forest training.

Ax Yuandong Zhang, Othmane Echchabi, Tianshu Feng, Wenyi Zhang, Hsuai-Kai Liao, Charles Chang 3/3/2026

Detecting Transportation Mode Using Dense Smartphone GPS Trajectories and Transformer Models

SpeedTransformer: Transformer-based model using smartphone GPS data to detect transportation modes, outperforming LSTM baselines.

Ax Yishan Wang, Tsai-Ning Wang, Mathias Funk, Aaqib Saeed 3/3/2026

StethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical Tasks

StethoLM: Audio language model for analyzing heart and lung sounds in clinical settings with improved interpretability over classification-only methods.

Ax Sourasekhar Banerjee, David Bergqvist, Salman Toor, Christian Rohner, Andreas Johnsson 3/3/2026

Quantifying Catastrophic Forgetting in IoT Intrusion Detection Systems

Studies catastrophic forgetting in IoT intrusion detection systems under distribution shifts from evolving attack patterns.

Ax Hutama Arif Bramantyo, Mukarram Ali Faridi, Rui Chen, Clarissa Harris, Yin Sun 3/3/2026

Deep Learning-Based Meat Freshness Detection with Segmentation and OOD-Aware Classification

Meat freshness detection system combining U-Net segmentation with OOD-aware classification from RGB images.

Ax Yinan Feng, Peng Jin, Yuzhe Guo, Yinpeng Chen, Youzuo Lin 3/3/2026

Improving Full Waveform Inversion in Large Model Era

Deep learning approach for full waveform inversion in seismic data using large models to overcome overfitting.

Ax Paul Nitschke, Shahriar Talebi 3/3/2026

Hereditary Geometric Meta-RL: Nonlocal Generalization via Task Symmetries

Geometric meta-RL approach leveraging task space symmetries for improved generalization in reinforcement learning.

Ax Hongjie Jiang, Di Luo 3/3/2026

TENG-BC: Unified Time-Evolving Natural Gradient for Neural PDE Solvers with General Boundary Conditions

TENG-BC neural PDE solver using time-evolving natural gradient with general boundary conditions for long-time accuracy.

Ax Tsao-Lun Chen, Chien-Liang Liu, Tzu-Ming Harry Hsu, Tai-Hsien Wu, Chi-Cheng Fu, Han-Yi E. Chou, Shun-Feng Su 3/3/2026

USE: Uncertainty Structure Estimation for Robust Semi-Supervised Learning

USE introduces lightweight procedure for semi-supervised learning that estimates uncertainty structure to handle out-of-distribution unlabeled data.

Ax Wenxin Li, Wenchao Liu, Chuan Wang, Qi Gao, Yin Ma, Hai Wei, Kai Wen 3/3/2026

Exact and Asymptotically Complete Robust Verifications of Neural Networks via Quantum Optimization

Quantum optimization approach for exact robust verification of neural networks against adversarial perturbations.

Ax Jeongho Bang, Kyoungho Cho 3/3/2026

Physics-Aware Learnability: From Set-Theoretic Independence to Operational Constraints

Theoretical analysis of learnability in machine learning incorporating operational constraints from physics.

Ax Dyah Adila, John Cooper, Alexander Yun, Avi Trost, Frederic Sala 3/3/2026

Weight Updates as Activation Shifts: A Principled Framework for Steering

Establishes equivalence between activation steering and weight-space updates, providing principled foundation for parameter-efficient LLM adaptation.

Ax Qing Luo, Fu Luo, Ke Li, Zhenkun Wang 3/3/2026

Efficient Decoder Scaling Strategy for Neural Routing Solvers

Studies decoder scaling strategies in construction-based neural routing solvers for vehicle routing optimization problems.

Ax Jinmyeong Shin, Joshua Tapia, Nicholas Ferreira, Gabriel Diaz, Moayed Daneshyari, Hyeran Jeon 3/3/2026

ROKA: Robust Knowledge Unlearning against Adversaries

ROKA addresses machine unlearning robustness against adversarial attacks that exploit knowledge contamination in unlearned models.

Ax Xi Wang, Wenbo Lu, Shengjie Wang 3/3/2026

Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training

RapTB improves GFlowNet training for fine-tuning LLMs by addressing prefix collapse through trajectory balancing and submodular replay.

Ax Xu Luo, Ji Zhang, Lianli Gao, Heng Tao Shen, Jingkuan Song 3/3/2026

Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols

FEWTRANS benchmark evaluates few-shot transfer learning of pre-trained models with improved evaluation protocols across 10 datasets.

Ax Khaleque Md Aashiq Kamal, Surya Eada, Aayushi Verma, Subek Acharya, Adrian Yemin, Benjamin Fuller, Kaleel Mahmood 3/3/2026

Analyzing Physical Adversarial Example Threats to Machine Learning in Election Systems

Analyzes adversarial example attacks against machine learning ballot classifiers in election systems.

Ax Achmad Ardani Prasha, Clavino Ourizqi Rachmadi, Sabrina Laila Mutiara, Hilman Syachr Ramadhan, Chareyl Reinalyta Borneo, Saruni Dwiasnati 3/3/2026

Dynamic Spatio-Temporal Graph Neural Network for Early Detection of Pornography Addiction in Adolescents Based on Electroencephalogram Signals

DST-GNN applies graph neural networks to detect pornography addiction in adolescents from EEG brain signals.

Ax Xianchao Xiu, Shenghao Sun, Xinrong Li, Jiyuan Tao 3/3/2026

Heaviside Low-Rank Support Matrix Machine

HL-SMM introduces Heaviside loss-based support matrix machine for classification of matrix-structured data with noise robustness.

Ax Kazuhiro Hiraki, Shinichi Ishihara, Takumi Kongo, Junnosuke Shino 3/3/2026

A Polynomial-Time Axiomatic Alternative to SHAP for Feature Attribution

ESENSC_rev2 proposes polynomial-time feature attribution algorithm as computationally efficient alternative to SHAP using game theory.

Ax Quoc Minh Nguyen, Trung Le, Jing Wu, Anh Tuan Bui, Mehrtash Harandi 3/3/2026

Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence

Antibody introduces defense mechanism against harmful fine-tuning attacks on LLMs by regularizing gradient contributions of poisoned samples.

Ax Wenhao Zheng, Wang Lu, Fangshuang Tang, Yiyang Lu, Jun Yang, Pengcheng Xiong, Yulan Yan 3/3/2026

Trinity: A Scenario-Aware Recommendation Framework for Large-Scale Cold-Start Users

Trinity addresses cold-start recommendation problems through feature engineering and model architecture for early-stage users.

Ax Ziquan Wang, Haobo Wang, Ke Chen, Lei Feng, Gang Chen 3/3/2026

FastBUS: A Fast Bayesian Framework for Unified Weakly-Supervised Learning

FastBUS proposes a Bayesian framework for weakly-supervised learning that handles multiple label types efficiently with batch processing.

Ax Lei Liu, Xiaoning Yu, Kang Chen, Jiahui Huang, Tengyuan Liu, Hongwei Zhao, Bin Li 3/3/2026

Phys-Diff: A Physics-Inspired Latent Diffusion Model for Tropical Cyclone Forecasting

Physics-inspired latent diffusion model for tropical cyclone forecasting incorporating physical constraints into predictions.

Ax Denis Blessing, Lorenz Richter, Julius Berner, Egor Malitskiy, Gerhard Neumann 3/3/2026

Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching

Bridge Matching Sampler for scalable sampling from unnormalized densities using generalized fixed-point diffusion matching.

Ax Atsuki Sato, Martin Aum\"uller, Yusuke Matsui 3/3/2026

Mathematical Foundations of Poisoning Attacks on Linear Regression over Cumulative Distribution Functions

Mathematical analysis of poisoning attacks on linear regression models used in learned index structures.

Ax Chenyu Zheng, Rongzhen Wang, Xinyu Zhang, Chongxuan Li 3/3/2026

Spectral Condition for $\mu$P under Width-Depth Scaling

Spectral condition analysis for maximal update parameterization under joint width-depth scaling in foundation models.

Ax Ray Telikani, Amir H. Gandomi 3/3/2026

Learning to Attack: A Bandit Approach to Adversarial Context Poisoning

AdvBandit black-box adaptive attack on neural contextual bandits formulating context poisoning as continuous-armed bandit problem.

Ax Yunqing Liu, Yi Zhou, Wenqi Fan 3/3/2026

Enhancing Molecular Property Predictions by Learning from Bond Modelling and Interactions

DeMol dual-graph framework for molecular property prediction incorporating bond-level phenomena like resonance and stereoselectivity.

Ax Jianheng Tang, Yajiang Huang, Kejia Fan, Feijiang Han, Jiaxu Li, Jinfeng Xu, Run He, Anfeng Liu, Houbing Herbert Song, Huiping Zhuang, Yunhuai Liu 3/3/2026

DeepAFL: Deep Analytic Federated Learning

Analytic federated learning approach replacing gradient-based updates with closed-form solutions for improved convergence and scalability.

Ax Chenhao Zhang, Muxing Li, Feng Liu, Weitong Chen, Miao Xu 3/3/2026

Unlearning Evaluation through Subset Statistical Independence

Subset-level evaluation framework for machine unlearning using statistical independence without retraining or membership inference.

Ax Patrick Stricker, Florian R\"ohrbein, Andreas Knoblauch 3/3/2026

Energy-Efficient Information Representation in MNIST Classification Using Biologically Inspired Learning

Study of energy-efficient representation learning in ANNs using biologically-inspired methods on MNIST classification.

Ax Li Sun, Lanxu Yang, Jiayu Tian, Bowen Fang, Xiaoyan Yu, Junda Ye, Peng Tang, Hao Peng, Philip S. Yu 3/3/2026

Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection

Policy-guided outlier synthesis approach for unsupervised out-of-distribution detection in graph neural networks.

Ax Li Sun, Zhenhao Huang, Silei Chen, Lanxu Yang, Junda Ye, Sen Su, Philip S. Yu 3/3/2026

Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models

Multi-domain graph pre-training framework for building graph foundation models with theoretical analysis of knowledge transfer.

Ax Zhanwang Liu, Yuting Li, Haoyuan Gao, Yexin Li, Linghe Kong, Lichao Sun, Weiran Huang 3/3/2026

IDER: IDempotent Experience Replay for Reliable Continual Learning

IDER method addressing catastrophic forgetting in continual learning with uncertainty calibration for mission-critical deployment.

Ax Yunzhong Qiu, Zhiyao Cen, Zhongyi Pei, Chen Wang, Jianmin Wang 3/3/2026

Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models

Data-centric framework for adapting diverse time series to large time series models without retraining.

Ax Cedric Damour 3/3/2026

Retrodictive Forecasting: A Proof-of-Concept for Exploiting Temporal Asymmetry in Time Series Prediction

Retrodictive forecasting paradigm using conditional VAE for time series prediction via inverse MAP optimization.

Ax Debjyoti Chakraborty 3/3/2026

Reward-Modulated Local Learning in Spiking Encoders: Controlled Benchmarks with STDP and Hybrid Rate Readouts

Empirical study of biologically-inspired local learning using STDP for spiking neural networks on digit recognition.

Ax Yijing Ke, Zihan Zhang, Ruosong Wang 3/3/2026

Frozen Policy Iteration: Computationally Efficient RL under Linear $Q^{\pi}$ Realizability for Deterministic Dynamics

Frozen Policy Iteration algorithm for computationally efficient reinforcement learning under linear Q-function realizability.

Ax Minkyoung Cho, Insu Jang, Shuowei Jin, Zesen Zhao, Adityan Jothi, Ethem F. Can, Min-Hung Chen, Z. Morley Mao 3/3/2026

MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search

MARS framework for efficient fine-tuning of multimodal LLMs using adaptive rank search to handle training imbalance across modalities.