Ax Sara Dragutinovi\'c, Rajesh Ranganath 3/3/2026

To Use or not to Use Muon: How Simplicity Bias in Optimizers Matters

Analysis of Muon optimizer's simplicity bias and potential downsides compared to Adam for neural network training.

Ax Alexander Strunk, Roland Assam 3/3/2026

General Proximal Flow Networks

Generalizes Bayesian Flow Networks with arbitrary divergence/distance functions replacing fixed KL divergence, enabling broader belief-update operators.

Ax Adam Marcus, Paul Agapow 3/3/2026

Identifying and Characterising Response in Clinical Trials: Development and Validation of a Machine Learning Approach in Colorectal Cancer

Combines partly conditional modeling with machine learning to identify patient response subgroups in colorectal cancer clinical trials using repeated measures.

Ax Karanpartap Singh, Adam Turnbull, Mohammad Abbasi, Kilian Pohl, Feng Vankee Lin, Ehsan Adeli 3/3/2026

Interpretable Cross-Network Attention for Resting-State fMRI Representation Learning

Self-supervised learning framework for resting-state fMRI using masked reconstruction with cross-attention for interpretable brain network representation learning.

Ax Gangani Ariyarathne, Isuru Ariyarathne, Greatness Emmanuel-King, Kate Lawal, Alexander C. Nwala 3/3/2026

Identifying the Geographic Foci of US Local News

Proposes geo-foci model for identifying salient geographical locations in US local news coverage to address economic pressures on local journalism.

Ax Shilong Tao, Zhe Feng, Shaohan Chen, Weichen Zhang, Zhanxing Zhu, Yunhuai Liu 3/3/2026

Neural Latent Arbitrary Lagrangian-Eulerian Grids for Fluid-Solid Interaction

Neural approach to fluid-solid interaction using latent arbitrary Lagrangian-Eulerian grids for capturing two-way nonlinear interactions in FSI problems.

Ax Nataly Brukhim, Nicol\`o Cesa-Bianchi, Carlo Ciliberto 3/3/2026

Lookahead identification in adversarial bandits: accuracy and memory bounds

Studies identification problem in adversarial multi-armed bandits for selecting arms performing best at future time with accuracy and memory bounds.

Ax Dariush Wahdany (CISPA Helmholtz Center for Information Security), Matthew Jagielski (Anthropic), Adam Dziedzic (CISPA Helmholtz Center for Information Security), Franziska Boenisch (CISPA Helmholtz Center for Information Security) 3/3/2026

Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning

Demonstrates membership inference attacks against data curation methods used for private ML, showing curation-based privacy solutions leak training data membership.

Ax Hossein Javidnia 3/3/2026

A Gauge Theory of Superposition: Toward a Sheaf-Theoretic Atlas of Neural Representations

Develops gauge-theoretic framework for superposition in LLMs using sheaf-theoretic atlas replacing single-global-dictionary with local semantic charts and Fisher metrics.

Ax Haimonti Dutta, Pruthvi Moluguri, Jin Dai, Saurabh Amarnath Mahindre 3/3/2026

GeMi: A Graph-based, Multimodal Recommendation System for Narrative Scroll Paintings

Graph Neural Network-based recommendation system for multimodal data handling content-based recommendations with user preference incorporation.

Ax Gianlucca Zuin, Adriano Veloso 3/3/2026

Navigating Time's Possibilities: Plausible Counterfactual Explanations for Multivariate Time-Series Forecast through Genetic Algorithms

Novel method for counterfactual learning in multivariate time series using genetic algorithms to uncover causal relationships and interventions.

Ax Idelfonso B. R. Nogueira, Carine M. Rebelloa, Mumin Enis Leblebici, Erick Giovani Sperandio Nascimento 3/3/2026

MultiPUFFIN: A Multimodal Domain-Constrained Foundation Model for Molecular Property Prediction of Small Molecules

Presents MultiPUFFIN, a domain-constrained multimodal foundation model for molecular property prediction ensuring thermodynamic consistency across chemical space.

Ax Yashvir S. Grewal, Daniel M. Steinberg, Thang D. Bui, Cheng Soon Ong, Edwin V. Bonilla 3/3/2026

Active Flow Matching

Introduces Active Flow Matching combining discrete diffusion/flow models with variational frameworks for black-box optimization without retraining.

Ax Michael Hardy, Yunsung Kim 3/3/2026

Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact

Evaluates performance misalignment between leading LLMs on out-of-distribution educational tasks, finding inter-model behaviors correlate higher than with human expert behaviors.

Ax Wenlong Chen 3/3/2026

Probabilistic Learning and Generation in Deep Sequence Models

Addresses uncertainty awareness in deep sequence models by integrating Bayesian methods with probabilistic learning, comparing approximate inference techniques.

Ax Zhiqi Yu, Xingping Liu, Haobin Mao, Mingshuo Liu, Long Chen, Jack Xin, Yifeng Yu 3/3/2026

Evaluating AI Grading on Real-World Handwritten College Mathematics: A Large-Scale Study Toward a Benchmark

Large-scale empirical study of AI grading on handwritten calculus work using OCR-conditioned LLMs with rubric-guided prompting for score and feedback generation.

Ax Ke Sun, Hongming Zhang, Jun Jin, Chao Gao, Xi Chen, Wulong Liu, Linglong Kong 3/3/2026

Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning

Proposes dual-learner framework combining fast learner and meta learner for continual RL, inspired by hippocampus-cortex interaction for knowledge transfer and integration.

Ax Joshua Steier 3/3/2026

When Does Margin Clamping Affect Training Variance? Dataset-Dependent Effects in Contrastive Forward-Forward Learning

Investigates margin clamping effects on training variance in Contrastive Forward-Forward learning for Vision Transformers, addressing instability sources.

Ax Hongzhan Chen, Tao Yang, Yuhua Zhu, Shiping Gao, Xiaojun Quan, Ting Yao 3/3/2026

Stabilizing Policy Optimization via Logits Convexity

Analyzes stability gap between supervised fine-tuning and RL in LLM training from gradient perspective, showing logits convexity role in stable optimization.

Ax Jiahao Fu, Feng Yang 3/3/2026

Intent-Context Synergy Reinforcement Learning for Autonomous UAV Decision-Making in Air Combat

Proposes Intent-Context Synergy RL approach for autonomous UAV decision-making in contested environments, addressing trade-offs between mission efficiency and survivability.

Ax Ashutosh Ranjan, Vivek Srivastava, Shirish Karande, Murari Mandal 3/3/2026

Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion Models

arXiv 2603.00975: Representation interference framework for selective unlearning in text-to-image diffusion models preserving quality.

Ax Xinwen Cheng, Jingyuan Zhang, Zhehao Huang, Yingwen Wu, Xiaolin Huang 3/3/2026

Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information

arXiv 2603.00992: Machine unlearning method for diffusion models removing sensitive concepts via mutual information elimination.

Ax Tony Hauptmann, Stefan Kramer 3/3/2026

Feature-Weighted Maximum Representative Subsampling

arXiv 2603.01013: Feature-weighted subsampling algorithm for debiasing studies when only subset of features are highly biased.

Ax Zhan Zhuang, Xiequn Wang, Zebin Chen, Feiyang Ye, Ying Wei, Kede Ma, Yu Zhang 3/3/2026

One-Token Verification for Reasoning Correctness Estimation

arXiv 2603.01025: One-token verification method for estimating correctness in LLM reasoning with reduced computational cost.

Ax Heewon Park, Mugon Joe, Miru Kim, Kyungjin Im, Minhae Kwon 3/3/2026

Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift

arXiv 2603.01040: Fed-ADE for federated learning adaptation under distribution shifts without ground-truth labels.

Ax Puhua Niu, Shili Wu, Xiaoning Qian 3/3/2026

Evaluating GFlowNet from partial episodes for stable and flexible policy-based training

arXiv 2603.01047: GFlowNet training improvements via partial episodes for stable policy-based sampling of combinatorial candidates.

Ax Tingrui Huang, Devendra Singh Dhami 3/3/2026

No More Maybe-Arrows: Resolving Causal Uncertainty by Breaking Symmetries

arXiv 2603.01052: CausalSAGE framework for refining causal discovery PAGs into DAGs by breaking symmetries.

Ax Lingfeng Li, Yin King Chu, Raymond Chan, Justin Wan 3/3/2026

A level-wise training scheme for learning neural multigrid smoothers with application to integral equations

arXiv 2603.01064: Level-wise training for neural multigrid smoothers applied to discretized integral equations.

Ax Seungju Back, Dongwoo Lee, Naun Kang, Taehee Lee, S. K. Hong, Youngjune Gwon, Sungjin Ahn 3/3/2026

Understanding LoRA as Knowledge Memory: An Empirical Analysis

arXiv 2603.01097: Empirical analysis of LoRA as parametric knowledge memory for continuous LLM updates without context constraints.

Ax Adithya Ramachandran, Satyaki Chatterjee, Thorkil Flensmark B. Neergaard, Maximilian Oberndoerfer, Andreas Maier, Siming Bayer 3/3/2026

A Deep Learning Framework for Heat Demand Forecasting using Time-Frequency Representations of Decomposed Features

arXiv 2603.01137: Deep learning framework for heat demand forecasting in district heating systems using time-frequency features.

Ax Hongyi Zhou, Kai Ye, Erhan Xu, Jin Zhu, Shijin Gong, Chengchun Shi 3/3/2026

Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic

arXiv 2603.01162: Theoretical analysis of GRPO through U-statistics lens, core method in DeepSeekMath and DeepSeek-R1 for LLM reasoning.

Ax Rong Fu, Chunlei Meng, Jinshuo Liu, Dianyu Zhao, Yongtai Liu, Yibo Meng, Xiaowen Ma, Wangyu Wu, Yangchen Zeng, Kangning Cui, Shuaishuai Cao, Simon Fong 3/3/2026

SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry

arXiv 2603.01168: SphUnc framework combining hyperspherical representation learning with causal modeling for uncertainty decomposition.

Ax Shailendra Bhandari 3/3/2026

PARWiS: Winner determination under shoestring budgets using active pairwise comparisons

arXiv 2603.01171: PARWiS algorithm for winner determination via active pairwise comparisons with reinforcement learning variant.

Ax Carlos Stein Brito 3/3/2026

Scaling of learning time for high dimensional inputs

arXiv 2603.01184: Theoretical analysis of learning time trade-offs for high-dimensional neural network inputs.

Ax Hrishikesh Viswanath, Hong Chul Nam, Xi Deng, Julius Berner, Anima Anandkumar, Aniket Bera 3/3/2026

Operator Learning Using Weak Supervision from Walk-on-Spheres

arXiv 2603.01193: Neural PDE solver training using Monte Carlo weak supervision via walk-on-spheres method.

Ax Isotta Magistrali, Fr\'ed\'eric Berdoz, Sam Dauncey, Roger Wattenhofer 3/3/2026

Subliminal Signals in Preference Labels

arXiv 2603.01204: Research on LLM-as-judge frameworks showing preference labels can function as covert communication channels between models.

Ax Yangzhen Wu, Shanda Li, Zixin Wen, Xin Zhou, Ameet Talwalkar, Yiming Yang, Wenhao Huang, Tianle Cai 3/3/2026

Learn Hard Problems During RL with Reference Guided Fine-tuning

arXiv 2603.01223: RL method for LLM mathematical reasoning using reference solutions to overcome reward sparsity in hard problems.

HN todsacerdoti 3/3/2026

Evolving Typst

Discussion on semantic versioning strategy for Typst markup language and decision to remain pre-1.0.

HN yuiegi 3/3/2026

Cloudflare uses lava lamps for randomness

Cloudflare's infrastructure article on using lava lamps as entropy source for randomness generation.

HN hypersnatch_dev 3/3/2026

Show HN: Offline desktop tool that extracts media endpoints from raw HTML

Offline desktop tool for extracting media endpoints from HTML without telemetry or cloud dependencies.

HN carlosladdz 3/3/2026

Show HN: AgentOx – MCP Security and Conformance Auditor

Open-source Rust CLI auditor for MCP servers, checking protocol conformance, security, and behavioral contracts before production deployment.

HN mooreds 3/3/2026

AI Authentication and Authorization

Article on applying OAuth/API identity patterns to secure AI systems and agents with authentication/authorization.

HN arm32 3/3/2026

Ed Gutenburg: The First Autonomous Investigative Reporter

Proposal for autonomous investigative reporter agents that can conduct research, publish findings, and pressure institutions on behalf of individual users.

HN matt_d 3/3/2026

Building an Open-Source Verilog Simulator with AI: 580K Lines in 43 Days

Engineer used AI agents to build open-source Verilog simulator with 580K lines in 43 days, including simulation, formal verification, and mutation testing capabilities.

LB blog.lyc8503.net via jcd 3/3/2026

Detecting LLM-Generated Web Novels Using "Classical" Machine Learning (AIGC Text Detection)

ML technique for detecting LLM-generated text using classical machine learning models. Includes online demo.

HN ddxv 3/3/2026

Ask HN: What Online LLM / Chat do you use?

Community discussion asking for recommendations on online LLM chat platforms beyond ChatGPT, Claude, and Grok.

HN VyperandUltron 3/3/2026

Prompt Vault – Save and organize your AI prompts ($9 Pro)

Commercial tool for storing and organizing prompts across multiple AI platforms with folder/tag organization and clipboard copying features.

HN SaaSasaurus 3/3/2026

Do AI Agents Make Money in 2026? Or Is It Just Mac Minis and Vibes?

Investigation into AI agent monetization claims in 2026, examining reality behind Mac Mini setups and autonomous income stream claims versus hype.

HN seagnson 3/3/2026

One-Stop Wan AI Video and Image Generator Platform

Platform aggregating Wan AI models for video and image generation from text prompts, images, or existing videos.

HN timr 3/3/2026

NY bill would prohibit AI chatbots from giving legal advice

New York bill proposes prohibiting AI chatbots from providing legal advice.