Ax Sijie Li, Weiwei Sun, Shanda Li, Ameet Talwalkar, Yiming Yang 3/2/2026

CoMind: Towards Community-Driven Agents for Machine Learning Engineering

CoMind introduces MLE-Live, a framework for evaluating LLM agents that engage with research communities in ML engineering tasks.

Ax Nathan Mitchell, Lander Ver Hoef, Imme Ebert-Uphoff, Kristina Moen, Kyle Hilburn, Yoonjin Lee, Emily J. King 3/2/2026

Knowledge-Guided Machine Learning: Illustrating the use of Explainable Boosting Machines to Identify Overshooting Tops in Satellite Imagery

Uses Explainable Boosting Machines to identify overshooting tops in satellite imagery for weather forecasting, emphasizing interpretability in high-stakes ML.

Ax Sajjad Ghiasvand, Mahnoosh Alizadeh, Ramtin Pedarsani 3/2/2026

pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models

pFedMMA proposes personalized federated fine-tuning with multi-modal adapters for vision-language models like CLIP on decentralized heterogeneous data.

Ax Paul Richmond, Prarit Agarwal, Borun Chowdhury, Vasilis Niarchos, Constantinos Papageorgakis 3/2/2026

FeynTune: Large Language Models for High-Energy Theory

20 fine-tuned Llama-3.1 8B variants specialized for High-Energy Physics, trained on arXiv abstracts with comparative domain analysis.

Ax Junming Yang, Ning Xu, Biao Liu, Shiqi Qiao, Xin Geng 3/2/2026

Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization

Research method for LLM alignment using meta-weighted online sampling to address distribution mismatch between offline data and evolving model policy.

Ax Shuofei Qiao, Yanqiu Zhao, Zhisong Qiu, Xiaobin Wang, Jintian Zhang, Zhao Bin, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen 3/2/2026

Scaling Generalist Data-Analytic Agents

DataMind framework trains scalable generalist data-analytic agents on diverse data formats for multi-step reasoning in scientific discovery.

Ax Laura Ying Schulz, Daniel Mitropolsky, Tomaso Poggio 3/2/2026

Unraveling Syntax: How Language Models Learn Context-Free Grammars

Study analyzing how language models learn context-free grammar structures and subgrammars during pretraining.

Ax Marcel Wien\"obst, Leonard Henckel, Sebastian Weichwald 3/2/2026

Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning

FLOP algorithm performs causal structure discovery for linear models using fast parent selection and discrete search optimization.

Ax Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han, Gufeng Zhang, Yanfei Chen, Wei Wang, Tomas Pfister, Chen-Yu Lee 3/2/2026

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Supervised Reinforcement Learning framework combines expert trajectories with step-wise reasoning to improve multi-step reasoning in open-source LLMs.

Ax Constanza Fierro, Fabien Roger 3/2/2026

Steering Language Models with Weight Arithmetic

Contrastive weight steering method edits LLM parameters via weight arithmetic for post-training behavior modification without expensive retraining.

Ax Aaron Miller, Sahil Kommalapati, Robert Moser, Petros Koumoutsakos 3/2/2026

Structure tensor Reynolds-averaged Navier-Stokes turbulence models with equivariant neural networks

Equivariant neural networks improve RANS turbulence model closures using structure tensors for better generalization in fluid dynamics.

Ax Rasmus F. Orsoe, Stephan Meighen-Berger, Jeffrey Lazar, Jorge Prado, Ivan Mozun-Mateo, Aske Rosted, Philip Weigel, Arturo Llorente Anaya 3/2/2026

NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes

NuBench open benchmark for deep learning-based event reconstruction in neutrino telescopes addressing inverse problems in particle physics.

Ax Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei, Truong Nguyen 3/2/2026

Score-Regularized Joint Sampling with Importance Weights for Flow Matching

Non-IID sampling framework for flow matching models to reduce variance in expectation estimation with limited sampling budgets.

Ax Juvenal Bassa, Arghya Chattopadhyay, Sudhir Malik, Mario Escabi Rivera 3/2/2026

MEDIC: a network for monitoring data quality in collider experiments

MEDIC applies machine learning for automated data quality monitoring and anomaly detection in particle physics collider experiments.

Ax Tanmay Ambadkar, {\DJ}or{\dj}e \v{Z}ikeli\'c, Abhinav Verma 3/2/2026

Automating the Refinement of Reinforcement Learning Specifications

AutoSpec framework automatically refines logical specifications for reinforcement learning agents to improve policy learning from under-specified tasks.

Ax Yu-Chao Hsu, Jiun-Cheng Jiang, Chun-Hua Lin, Kuo-Chung Peng, Nan-Yow Chen, Samuel Yen-Chi Chen, En-Jui Kuo, Hsi-Sheng Goan 3/2/2026

QKAN-LSTM: Quantum-inspired Kolmogorov-Arnold Long Short-term Memory

QKAN-LSTM combines quantum-inspired methods with Kolmogorov-Arnold networks for improved sequential modeling with reduced parameter redundancy.

Ax Liping Tao, Xindi Tong, Chee Wei Tan 3/2/2026

Learning to Optimize by Differentiable Programming

Tutorial on using differentiable programming frameworks like PyTorch and JAX to learn and design optimization algorithms automatically.

Ax Thomas Ziller, Shashikant Ilager, Alessandro Tundo, Ezio Bartocci, Leonardo Mariani, Ivona Brandic 3/2/2026

GreenServ: Energy-Efficient Context-Aware Dynamic Routing for Multi-Model LLM Inference

GreenServ proposes dynamic routing framework for efficient multi-model LLM inference using context-aware model selection to reduce energy consumption.

Ax Quanquan Peng, Yunfeng Lin, Yufei Xue, Jiangmiao Pang, Weinan Zhang 3/2/2026

Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control

Research on training humanoid robots with reinforcement learning to handle diverse embodiments and complex behaviors through distillation methods.

Ax Azmine Toushik Wasi, Wahid Faisal, Abdur Rahman, Mahfuz Ahmed Anik, Munem Shahriar, Mohsin Mahmud Topu, Sadia Tasnim Meem, Rahatun Nesa Priti, Sabrina Afroz Mitu, Md. Iqramul Hoque, Shahriyar Zaman Ridoy, Mohammed Eunus Ali, Majd Hawasly, Mohammad Raza, Md Rizwan Parvez 3/2/2026

SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

SpatiaLab benchmark evaluates vision-language models' spatial reasoning capabilities on real-world tasks with visual noise and diverse spatial relationships.

Ax Runze Tang, Penny Sweetser 3/2/2026

Flow-Enabled Generalization to Human Demonstrations in Few-Shot Imitation Learning

SpatiaLab: benchmark evaluating vision-language model spatial reasoning on complex real-world visual scenarios.

Ax Ramansh Sharma, Matthew Lowery, Houman Owhadi, Varun Shankar 3/2/2026

Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows

Flow-based intermediate representation for few-shot robot imitation learning from human video demonstrations.

Ax Guoxuan Ma, Yuan Zhong, Moyan Li, Yuxiao Nie, Jian Kang 3/2/2026

Sparse Bayesian Modeling of EEG Channel Interactions Improves P300 Brain-Computer Interface Performance

Property-preserving kernel operator learning for incompressible Navier-Stokes flow simulation and surrogate modeling.

Ax Danil Akhtiamov, Reza Ghane, Omead Pooladzandi, Babak Hassibi 3/2/2026

Implicit Bias and Convergence of Matrix Stochastic Mirror Descent

SceneTok: tokenizer encoding 3D scene views into compressed, permutation-invariant tokens for diffusion models.

Ax Xiang Li, Zikai Wei, Yiyan Qi, Wanyun Zhou, Xiang Liu, Penglei Sun, Jian Guo, Yongqi Zhang, Xiaowen Chu 3/2/2026

Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling

Theoretical analysis of stochastic mirror descent convergence with matrix parameters in overparameterized regime.

Ax Tony Feng, Junehyuk Jung, Sang-hyun Kim, Carlo Pagano, Sergei Gukov, Chiang-Chiang Tsai, David Woodruff, Adel Javanmard, Aryan Mokhtari, Dawsen Hwang, Yuri Chervonyi, Jonathan N. Lee, Garrett Bingham, Trieu H. Trinh, Vahab Mirrokni, Quoc V. Le, Thang Luong 3/2/2026

Aletheia tackles FirstProof autonomously

Janus-Q uses event-driven hierarchical reward modeling with textual signals for financial market trading.

Ax Sumin Kim, Jihoon Kwon, Yoon Kim, Nicole Kagan, Raffi Khatchadourian, Wonbin Ahn, Alejandro Lopez-Lira, Jaewon Lee, Yoontae Hwang, Oscar Levy, Yongjae Lee, Chanyeol Choi 3/2/2026

Forecasting Future Language: Context Design for Mention Markets

Aletheia, Gemini 3 Deep Think-powered math research agent, autonomously solved 6 of 10 FirstProof challenge problems.

Ax Willem Schooltink, Fabio Massimo Zennaro 3/2/2026

Multi-Level Causal Embeddings

Research on context design for LLM-based probabilistic forecasting in mention prediction markets.

Ax Zezhou Wang, Youjie Li, Zhiqi Lin, Jiacheng Yang, Cong Xie, Guanyu Feng, Zheng Zhong, Ziyue Huang, Hongyu Zhu, Zhi Zhang, Yanghua Peng, Xin Liu 3/2/2026

veScale-FSDP: Flexible and High-Performance FSDP at Scale

Framework for multi-level causal embeddings enabling mapping of detailed models into coarser causal model sub-systems.

Ax Bangrui Xu, Qihang Yao, Zirui Tang, Xuanhe Zhou, Yeye He, Shihan Yu, Qianqian Xu, Bin Wang, Guoliang Li, Conghui He, Fan Wu 3/2/2026

MoDora: Tree-Based Semi-Structured Document Analysis System

veScale-FSDP improves fully sharded data parallel training flexibility for structure-aware methods and advanced optimizers.

HN enveil 3/2/2026

Show HN:Enveil–Encrypted vault that replaces .env files with runtime injection

Enveil is a self-hosted encrypted environment variable manager replacing .env files with runtime injection for secure secret management.

HN yashpxl 3/2/2026

Is anyone compressing AI models for the 4B people without GPUs or internet?

Developer exploring model compression techniques to make AI accessible without GPUs/internet. References DeepSeek distillation and Samsung TRM research.

HN mafia15 3/2/2026

Show HN: I built open source Gmail organizer because I refused to pay $30/month

Open-source Gmail organizer with auto-labeling and draft replies. Runs locally within Gmail. LLM application for email automation.

HN BuddhikaR 3/2/2026

Show HN: PrivacyShield – Mask your PII before it reaches ChatGPT/Claude

Chrome extension detecting 15+ PII types before sending to Claude/ChatGPT. Local processing with AES-256 encryption. Privacy tool for LLM use.

HN bfzli 3/2/2026

ClawHost – One-click, self-hosted OpenClaw deployments you own

Open-source platform simplifying self-hosted OpenClaw deployment with one-click setup. Infrastructure tooling but unclear OpenClaw connection to AI interests.

HN schmuhblaster 3/2/2026

Static taint analysis for LLM agents

DeepClause: Tool for compiling Markdown into DML (Prolog-based language) for orchestrating LLM agents securely. Combines DSPy, CodeAct, Prolog with static taint analysis.

HN umairnadeem123 3/2/2026

Show HN: HN Bot Detector - Detects LLM-Generated Comments on Hacker News

HN Bot Detector: Tool to identify LLM-generated comments using n-gram TF-IDF and heuristics. Scores comments 0-100 on likelihood of AI generation.

HN AluminatiAi 3/2/2026

Show HN: AluminatiAi – Per-job GPU energy cost tracking (open source)

AluminatiAi: Open source Python agent for per-job GPU energy cost tracking. Monitors power consumption and converts to dollar costs via dashboard.

HN ZeroDayCyber 3/2/2026

Show HN: AI agent that works autonomously while I'm offline

Autonomous AI agent running offline with persistent memory, goal-setting, and planning. Built landing pages, Stripe setup, blog posts autonomously during flight.

HN oldeucryptoguy 3/2/2026

Show HN: Laid – Chrome extension that detects AI-generated LinkedIn posts

Laid: Chrome extension detecting AI-generated LinkedIn posts using local heuristics or LLM providers. Assigns likelihood scores to feed posts.

HN thequert 3/2/2026

Show HN: Cc-reaper – Three-layer cleanup for orphan Claude Code processes

Cc-reaper: Automated cleanup tool for orphan Claude Code processes and MCP servers. Prevents memory leaks from abandoned agent sessions.

HN edgar_ortega 3/2/2026

Show HN: Ralphex – autonomous GPT Codex agent loop for ChatGPT Pro users

Ralphex: Autonomous GPT Codex agent loop for ChatGPT Pro users. Budget-friendly alternative to Claude Code with git-based memory persistence.

HN p1esk 3/2/2026

Ask HN: When do you expect ChatGPT moment in robotics?

Discussion on robotics progress toward AGI-like capabilities. Mentions Physical Intelligence and Generalist AI startups reaching GPT-3 level performance.

HN sunch 3/2/2026

Show HN: Simaic – AI back end with memory, 90s setup for Cursor/Windsurf

SIMAIC: AI backend with memory system and structured JSON output for chatbots/agents. Supports Discord, Line, Web. Built by 17-year-old developer.

HN aretedriver 3/2/2026

Show HN: Agent-Audit – Lint and cost-estimate your AI agent

CLI tool detecting anti-patterns and estimating costs in agent workflow YAML configs before execution.

HN dahjelle 3/2/2026

Secure LLM Scripting. Finally

Security framework for LLM agents enabling secure data tracking and enforcement without proprietary abstractions.

HN deepseekai 3/2/2026

Show HN: Anime AI Agent for end-to-end anime short creation

AI agent orchestrating end-to-end anime creation via script writing, storyboarding, image generation, and video output.

HN anand_pattern 3/2/2026

Show HN: Sun – Realtime voice agent for group conservation not just turn taking

Sun: Realtime voice agent for group conversation. Minimal details provided in title only.

HN raphaelty 3/2/2026

A semantic Code Search CLI but with grep filters

ColGREP: Semantic code search CLI using multi-vector search with regex filtering. Local-only, single Rust binary for coding agents. Built on NextPlaid.

HN mohsen1 3/2/2026

Show HN: I used LLMs to build a compression tool that beats xz on x86_64 ELFs

Compression tool using LLMs (ChatGPT, Gemini) to optimize x86_64 ELF binary compression beyond xz through structural analysis.