HN mastercoder8 4/29/2026

Q: A Slim LLM CLI; For asking and debugging from cli directly

Q: slim shell-based LLM CLI for terminal queries with session logging and secret redaction.

HN ash_ai 4/29/2026

Update on AgentCheck

AgentCheck: pytest-style testing framework for AI agent behavior validation and regression testing.

HN maruakshay 4/29/2026

I built OWASP-style security skill packs for LLM apps (NPM install)

NPM package providing 18 security skill packs for reviewing and hardening LLM applications.

HN noiv 4/29/2026

IBM Bob: AI Development Partner

IBM Bob: AI development partner covering full software development lifecycle with enterprise governance and security controls.

HN nvader 4/29/2026

Rust Bucket: Agent-first Rust project bootstrapper

Rust Bucket: Agent-first Rust project bootstrapper for rapid project initialization.

HN SyntheticOutlaw 4/29/2026

$2,500 bug bounty for real-world AI misalignment

Bug bounty program offering up to $2,500 for documenting real-world AI misalignment cases and safety failures.

HN 1vuio0pswjnm7 4/29/2026

Tech is in turmoil but the rest of corporate America isn't

Analysis of AI-driven tech layoffs and workforce displacement, contrasting Silicon Valley narrative with broader corporate adoption.

HN justus_bluemer 4/29/2026

Mistral Workflows: durable AI orchestration built on Temporal

Mistral Workflows: enterprise orchestration layer for AI agents built on Temporal, enabling production-ready durable AI processes.

HN gmays 4/29/2026

Perplexity Builds Accuracy into Frontier AI

Perplexity research on search-augmented LLMs for improving frontier AI model accuracy in knowledge-intensive tasks.

HN ekadagami 4/29/2026

PTP/1.0 – Prompt Transport Protocol

Informational RFC proposing Prompt Transport Protocol for transmitting intents and hints for local generative model reconstruction.

HN canaddons 4/29/2026

What If Your OS Could Think?

Browser-based operating system with integrated AI agent (DAEMON) capable of building apps and managing files autonomously.

HN thepoors 4/29/2026

Artificial Inteligence that works (maybe)

Conceptual architecture for AI systems based on version-controlled knowledge base with provenance and rights management.

HN septisum 4/29/2026

ChatGPT/Gemini can now draw on your screen to help you navigate complex software

SketchVLM: framework enabling vision-language models to produce editable SVG overlays explaining visual reasoning on input images.

HN AlenzhanJ 4/29/2026

The versioned filesystem for AI agents

Coregit provides versioned filesystem for AI agents with git-based commits, forks, and time-travel snapshots via REST API.

Ax Sungwoo Jung, Seonil Son 4/29/2026

How Much Heavy Lifting Can an Agent Harness Do?: Measuring the LLM's Residual Role in a Planning Agent

Analysis measuring how much agent harnesses versus LLMs contribute to planning agent performance on fixed models.

Ax Fanqi Kong, Weiqin Zu, Xinyu Chen, Yaodong Yang, Song-Chun Zhu, Xue Feng 4/29/2026

SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning

SIV-Bench video benchmark for evaluating multimodal large language models on social interaction understanding and reasoning tasks.

Ax Shaotian Li, Shangze Li, Chuancheng Shi, Wenhua Wu, Yanqiu Wu, Xiaohan Yu, Fei Shen, Tat-Seng Chua 4/29/2026

Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models

Research on internal mechanisms of vision-language models for anomaly detection, identifying sparse neurons without external adapters.

Ax Taeyoung Kim 4/29/2026

Loop Corrections to the Training Error and Generalization Gap of Random Feature Models

Statistical physics analysis of random feature models investigating training and test error beyond mean kernel approximation.

Ax Sepideh Abedini, M. Tamer \"Ozsu 4/29/2026

A Demonstration of SQLyzr: A Platform for Fine-Grained Text-to-SQL Evaluation and Analysis

SQLyzr platform for fine-grained evaluation and analysis of text-to-SQL models built on LLMs, providing detailed insights beyond aggregate benchmark scores.

Ax Abdul Jabbar, Ethan Grooby, Yang Yi Poh, Khawza I. Ahmad, Md Hassanuzzaman, Raqibul Mostafa, Ahsan H. Khandoker, Faezeh Marzbanrad 4/29/2026

Automated detection of pediatric congenital heart disease from phonocardiograms using deep and handcrafted feature fusion

Deep learning method for automated congenital heart disease detection from phonocardiograms using feature fusion.

Ax Ramanath Garai, Iswari Sahu, S. Chakraverty 4/29/2026

Comparative Study of Bending Analysis using Physics-Informed Neural Networks and Numerical Dynamic Deflection in Perforated nanobeam

Physics-Informed Neural Networks compared with numerical methods for analyzing bending behavior in perforated nanobeams.

Ax Yiqian Liu, Jiayi Niu, Adam Kelleher, Subhabrata Das 4/29/2026

Liquid Neural Network Models for Natural Gas Spot Price Time-Series Forecasting

Liquid Neural Networks applied to natural gas spot price forecasting, addressing nonlinear dynamics and regime changes in time-series prediction.

Ax Molena Huynh 4/29/2026

Query-Efficient Quantum Approximate Optimization via Graph-Conditioned Trust Regions

Graph-conditioned trust-region method reduces query costs for low-depth Quantum Approximate Optimization Algorithm implementations.

Ax Peng Liao, Peijia Zheng, Lingbo Li, Shangsong Liang, Lin Chen 4/29/2026

Intrinsic Mutual Information as a Modulator for Preference Optimization

Intrinsic Mutual Information used as modulator for preference optimization in Large Language Models with reduced hyperparameter tuning.

Ax Martin G. Frasch 4/29/2026

minAction.net: Energy-First Neural Architecture Design -- From Biological Principles to Systematic Validation

Energy-aware neural architecture design evaluated across 2,203 experiments, optimizing for computational cost alongside accuracy in ML models.

Ax Maixent Chenebaux 4/29/2026

Nautile-370M: Spectral Memory Meets Attention in a Small Reasoning Model

Nautile-370M is a 371M-parameter language model combining spectral memory and attention for efficient reasoning with strict parameter budgets.

Ax Grigorios Papanikolaou, Ioannis Kontopoulos, Konstantinos Tserpes 4/29/2026

A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks

Comparative analysis of Upper Confidence Bound algorithms in Adaptive Deep Neural Networks for energy-efficient edge computing inference.

Ax Xiaoyi Wang, Zhiqiang Wang, Jianqing Liang, Xingwang Zhao, Chuangyin Dang, Zhen Jin, Jiye Liang 4/29/2026

Time-varying Interaction Graph ODE for Dynamic Graph Representation Learning

Time-varying graph neural ODE framework for dynamic graph representation learning with adaptive message passing mechanisms.

Ax Bojie Li 4/29/2026

Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity

Method to estimate closed-source LLM parameter counts by measuring factual capacity, providing tighter bounds than inference economics.

Ax Yuxiang Wang, Yu Xiang, Baojian Zhou, Qifang Zhao, Keyue Jiang, Yanghua Xiao, Xiaoxiao Xu 4/29/2026

On the Trainability of Masked Diffusion Language Models via Blockwise Locality

Study of masked diffusion language models with blockwise locality, comparing training stability and structured generation against autoregressive LLMs.

Ax Minkyu Kim, Vincent-Daniel Yun, Youngrae Kim, Youngjin Heo, Suin Cho, Seong-hun Kim, Woosang Lim, Gaeul Kwon 4/29/2026

Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning

Depth pruning for LLMs that treats layer redundancy functionally relative to evaluation objectives rather than as inherent structural property.

Ax NVIDIA, :, Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki, Matthieu Le, Tyler Poon, Danial Mohseni Taheri, Ilia Karmanov, Guilin Liu, Jarno Seppanen, Arushi Goel, Mike Ranzinger, Greg Heinrich, Guo Chen, Lukas Voegtle, Philipp Fischer, Timo Roman, Karan Sapra, Collin McCarthy, Shaokun Zhang, Fuxiao Liu, Hanrong Ye, Yi Dong, Mingjie Liu, Yifan Peng, Piotr Zelasko, Zhehuai Chen, Nithin Rao Koluguri, Nune Tadevosyan, Lilit Grigoryan, Ehsan Hosseini Asl, Pritam Biswas, Leili Tavabi, Yuanhang Su, Zhiding Yu, Peter Jin, Alexandre Milesi, Netanel Haber, Yao Xu, Sarah Amiraslani, Nabin Mulepati, Eric Tramel, Jaehun Jung, Ximing Lu, Brandon Cui, Jin Xu, Zhiqi Li, Shihao Wang, Yuanguo Kuang, Shaokun Zhang, Huck Yang, Boyi Li, Hongxu Yin, Song Han, Pavlo Molchanov, Adi Renduchintala, Charles Wang, David Mosallanezhad, Soumye Singhal, Luis Vega, Katherine Cheung, Sreyan Ghosh, Yian Zhang, Alexander Bukharin, Venkat Srinivasan, Johnny Greco, Andre Manoel, Maarten Van Segbroeck, Suseella Panguliri, Rohit Watve, Divyanshu Kakwani, Shubham Pachori, Jeffrey Glick, Radha Sri-Tharan, Aileen Zaman, Khanh Nguyen, Shi Chen, Jiaheng Fang, Qing Miao, Wenfei Zhou, Yu Wang, Zaid Pervaiz Bhat, Varun Praveen, Arihant Jain, Ramanathan Arunachalam, Tomasz Kornuta, Ashton Sharabiani, Amy Shen, Wei Huang, Yi-Fu Wu, Ali Roshan Ghias, Huiying Li, Brian Yu, Nima Tajbakhsh, Chen Cui, Wenwen Gao, Li Ding, Terry Kong, Manoj Kilaru, Anahita Bhiwandiwalla, Marek Wawrzos, Daniel Korzekwa, Pablo Ribalta, Grzegorz Chlebus, Besmira Nushi, Ewa Dobrowolska, Maciej Jakub Mikulski, Kunal Dhawan, Steve Huang, Jagadeesh Balam, Yongqiang Wang, Nikolay Karpov, Valentin Mendelev, George Zelenfroynd, Meline Mkrtchyan, Qing Miao, Omri Almog, Bhavesh Pawar, Rameshwar Shivbhakta, Sudeep Sabnis, Ashrton Sharabiani, Negar Habibi, Geethapriya Venkataramani, Pamela Peng, Prerit Rodney, Serge Panev, Richard Mazzarese, Nicky Liu, Michael Fukuyama, Andrii Skliar, Roger Waleffe, Duncan Riach, Yunheng Zou, Jian Hu, Hao Zhang, Binfeng Xu, Yuhao Yang, Zuhair Ahmed, Alexandre Milesi, Carlo del Mundo, Chad Voegele, Zhiyu Cheng, Nave Assaf, Andrii Skliar, Daniel Afrimi, Natan Bagrov, Ran Zilberstein, Ofri Masad, Eugene Khvedchenia, Natan Bagrov, Borys Tymchenko, Tomer Asida, Daniel Afrimi, Parth Mannan, Victor Cui, Michael Evans, Katherine Luna, Jie Lou, Pinky Xu, Guyue Huang, Negar Habibi, Michael Boone, Pradeep Thalasta, Adeola Adesoba, Dina Yared, Christopher Parisien, Leon Derczynski, Shaona Ghosh, Wes Feely, Micah Schaffer, Radha Sri-Tharan, Jeffrey Glick, Barnaby Simkin, George Zelenfroynd, Tomasz Grzegorzek, Rishabh Garg, Aastha Jhunjhunwala, Sergei Kolchenko, Farzan Memarian, Haran Kumar, Shiv Kumar, Isabel Hulseman, Anjali Shah, Kari Briski, Padmavathy Subramanian, Joey Conway, Udi Karpas, Jane Polak Scowcroft, Annie Surla, Shilpa Ammireddy, Ellie Evans, Jesse Oliver, Tom Balough, Chia-Chih Chen, Sandip Bhaskar, Alejandra Rico, Bardiya Sadeghi, Seph Mard, Katherine Cheung, Meredith Price, Laya Sleiman, Saori Kaji, Wesley Helmholz, Wendy Quan, Michael Lightstone, Jonathan Cohen, Jian Zhang, Oleksii Kuchaiev, Boris Ginsburg, Jan Kautz, Eileen Long, Mohammad Shoeybi, Mostofa Patwary, Oluwatobi Olabiyi, Andrew Tao, Bryan Catanzaro, Udi Karpas 4/29/2026

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

Nemotron 3 Nano Omni: open multimodal model supporting audio, text, images, and video with improvements in document understanding and localization.

Ax Adam Ousherovitch, Ambuj Tewari 4/29/2026

Compute Aligned Training: Optimizing for Test Time Inference

Compute Aligned Training method that aligns LLM post-training objectives with test-time inference procedures that aggregate multiple outputs.

Ax Dongze Wu, Linglingzhi Zhu, Yao Xie 4/29/2026

CoreFlow: Low-Rank Matrix Generative Models

CoreFlow: geometry-preserving low-rank flow model for learning matrix-valued distributions from high-dimensional incomplete data.

Ax Lawrence Keunho Jang, Jing Yu Koh, Daniel Fried, Ruslan Salakhutdinov 4/29/2026

Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks

Odysseys benchmark for evaluating web agents on realistic long-horizon multi-site tasks requiring cross-domain reasoning and sustained context.

Ax Ishan Patel, Ishan Joshi 4/29/2026

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference

PolyKV system enabling multiple concurrent LLM agents to share compressed KV cache pool, reducing memory overhead for multi-agent inference.

Ax Shiyi Du, Jiayuan Liu, Weihua Du, Yue Huang, Jiayi Li, Yingtao Luo, Xiangliang Zhang, Vincent Conitzer, Carl Kingsford 4/29/2026

Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors

SWIFT framework that transfers learned workflow topologies across tasks instead of searching per-task, reducing computational cost for agentic workflow design.

Ax Christian Lysenst{\o}en 4/29/2026

Feasible-First Exploration for Constrained ML Deployment Optimization in Crash-Prone Hierarchical Search Spaces

Feasible-first exploration for ML model deployment optimization handling hierarchical search spaces with invalid configurations.

Ax Keenan Powell, Peihong Yu, Pratap Tokekar 4/29/2026

Zero Shot Coordination for Sparse Reward Tasks with Diverse Reward Shapings

Zero-shot coordination training for multi-agent RL to cooperate with unknown agents in sparse reward tasks.

Ax Wenshuo Wang 4/29/2026

Knowledge Distillation Must Account for What It Loses

Position paper arguing knowledge distillation must evaluate preserved teacher capabilities beyond task metrics for reliable deployment.

Ax Sicheng Dai, Kai Chen, Hongwang Xiao, Shan Yu, Qiwei Ye 4/29/2026

Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation

Low-rank adaptation approach for unified multi-task EEG analysis with self-supervised pre-trained models.

Ax Laure Berti-Equille 4/29/2026

Prior-Aligned Data Cleaning for Tabular Foundation Models

Data cleaning method for tabular foundation models addressing missing values, outliers, and duplicates to improve zero-shot accuracy.

Ax Divake Kumar, Sina Tayebati, Devashri Naik, Ranganath Krishnan, Amit Ranjan Trivedi 4/29/2026

VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation

Analyzes reliability of Vision-Language Models as evaluation judges using conformal prediction to provide calibrated uncertainty intervals.

Ax Chenbo Yu 4/29/2026

DGLight: DQN-Guided GRPO Fine-Tuning of Large Language Models for Traffic Signal Control

DGLight framework combines DQN critic with reinforcement learning to fine-tune LLMs for traffic signal control optimization.

Ax Sehyeon Oh, Yongin Kwon, Jemin Lee 4/29/2026

QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention

Integer-only quantization approach for FlashAttention in vision transformers addressing scale explosion and numerical stability challenges.

Ax Hongfei Wu, Ruijian Han, Yancheng Yuan 4/29/2026

VAE-Inf: A statistically interpretable generative paradigm for imbalanced classification

VAE-based two-stage framework for imbalanced classification combining generative and discriminative modeling.

Ax Xingjian Hu, Zuoyu Yan, Jianhua Zhu, Liangcai Gao, Fei Wang, Tengfei Ma 4/29/2026

GraphPL: Leveraging GNN for Efficient and Robust Modalities Imputation in Patchwork Learning

GNN-based approach for imputing missing modalities in patchwork learning where different clients have varying modality availability.

Ax Yeeun Lim, Narim Jeong, Donghwan Lee 4/29/2026

Safe-Support Q-Learning: Learning without Unsafe Exploration

Safe RL method preventing unsafe state visitation during training via Q-learning with strict safety constraints.

Ax Julia Berger, Bernd Frauenknecht, Sebastian Trimpe, Bastian Leibe 4/29/2026

Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Space Models

Analyzes limitations of epistemic uncertainty quantification in latent space models for model-based RL with image observations.

Ax Changyu Li, Shuanghong Huang, Jiashen Liu, Ming Lei, Jidu Xing, Kaishun Wu, Lu Wang, Fei Luo 4/29/2026

FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices

Fisher-guided token quantization for efficient federated fine-tuning of LLMs on edge devices with heterogeneous bandwidth constraints.