Ax Anubhab Ghosh, Yonina C. Eldar, Saikat Chatterjee 4/7/2026

pDANSE: Particle-based Data-driven Nonlinear State Estimation from Nonlinear Measurements

Data-driven nonlinear state estimation method for model-free processes using RNNs with noisy nonlinear measurements.

Ax Ilyass Moummad, Kawtar Zaher, Herv\'e Go\"eau, Alexis Joly 4/7/2026

Image Hashing via Cross-View Code Alignment in the Age of Foundation Models

Image hashing method using foundation models for efficient large-scale retrieval with compact binary codes instead of high-dimensional embeddings.

Ax Saeedeh Javadi, Sara Mirabi, Manan Gangar, Bahadorreza Ofoghi 4/7/2026

Contradictions in Context: Challenges for Retrieval-Augmented Generation in Healthcare

Study of RAG limitations in healthcare domain, showing how retrieval-augmented generation fails when source documents contain contradictory or outdated information.

Ax Md Tanvirul Alam, Saksham Aggarwal, Justin Yang Chae, Nidhi Rastogi 4/7/2026

SPHINX: A Synthetic Environment for Visual Perception and Reasoning

Sphinx synthetic environment for visual perception and reasoning with procedurally generated puzzles covering 25 task types, enabling precise evaluation and large-scale dataset construction.

Ax Ivan Yee Lee, Cheng Yang, Taylor Berg-Kirkpatrick 4/7/2026

Optical Context Compression Is Just (Bad) Autoencoding

Analysis showing optical context compression via vision tokens is functionally equivalent to lossy autoencoding, questioning effectiveness of DeepSeek-OCR's compression pipeline.

Ax Leijie Wang, Otilia Stretcu, Wei Qiao, Thomas Denby, Krishnamurthy Viswanathan, Enming Luo, Chun-Ta Lu, Tushar Dogra, Ranjay Krishna, Ariel Fuxman 4/7/2026

Agile Deliberation: Concept Deliberation for Subjective Visual Classification

Human-in-the-loop approach for visual classification through iterative concept deliberation, addressing subjective vision tasks in content moderation and curation.

Ax Benjamin C. Koenig, Sili Deng 4/7/2026

Learning continuous state of charge dependent thermal decomposition kinetics for Li-ion cathodes using Kolmogorov-Arnold Chemical Reaction Neural Networks (KA-CRNNs)

Application of Kolmogorov-Arnold neural networks to model thermal decomposition kinetics in lithium-ion batteries with state-of-charge dependence.

Ax Benyamin Hosseiny, Kamirul Kamirul, Odysseas Pappas, Alin Achim 4/7/2026

NASTaR: NovaSAR Automated Ship Target Recognition Dataset

Synthetic Aperture Radar dataset for ship type classification using deep learning models, focused on maritime activity monitoring.

Ax Rahul Baxi 4/7/2026

The Drill-Down and Fabricate Test (DDFT): A Protocol for Measuring Epistemic Robustness in Language Models

DDFT protocol measures epistemic robustness of language models under stress conditions, distinguishing knowledge gaps from verification mechanism failures beyond static benchmarks.

Ax Binxu Wang, Jingxuan Fan, Xu Pan 4/7/2026

Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers

Mechanistic interpretability study of how Diffusion Transformers generate correct spatial relations in text-to-image generation.

Ax Mayank Sharma, Roy Pea, Hari Subramonyam 4/7/2026

ConvoLearn: A Dataset for Fine-Tuning Dialogic AI Tutors

ConvoLearn dataset of 2,134 tutor-student dialogues for fine-tuning dialogue-based AI tutors grounded in knowledge-building theory.

Ax Viacheslav Sydora, Guner Dilsad Er, Michael Muehlebach 4/7/2026

Teaching Machine Learning Fundamentals with LEGO Robotics

Open-source educational platform teaching ML fundamentals to students aged 12-17 using LEGO robotics.

Ax Ellen Xiaoqing Tan, Jack Lanchantin, Shehzaad Dhuliawala, Danwei Li, Thao Nguyen, Jing Xu, Ping Yu, Ilia Kulikov, Sainbayar Sukhbaatar, Jason Weston, Xian Li, Olga Golovneva 4/7/2026

Self-Improving Pretraining: using post-trained models to pretrain better models

Pretraining approach using post-trained models to incorporate reasoning and safety behaviors earlier in LLM development.

Ax Zixuan Xia, Hao Wang, Pengcheng Weng, Yanyu Qian, Yangxin Xu, William Dan, Fei Wang 4/7/2026

Improving Multimodal Learning with Dispersive and Anchoring Regularization

Regularization techniques for improving multimodal representation learning by addressing collapse and inconsistency issues.

Ax Henri A\"idasso, Francis Bordeleau, Ali Tizghadam 4/7/2026

Predicting Intermittent Job Failure Categories for Diagnosis Using Few-Shot Fine-Tuned Language Models

Few-shot fine-tuned language models for diagnosing intermittent CI pipeline failures in software development.

Ax Ilyass Moummad, Marius Miron, David Robinson, Kawtar Zaher, Herv\'e Go\"eau, Olivier Pietquin, Pierre Bonnet, Emmanuel Chemla, Matthieu Geist, Alexis Joly 4/7/2026

Compact Hypercube Embeddings for Fast Text-based Wildlife Observation Retrieval

Compact embeddings for fast text-based wildlife observation retrieval from large biodiversity archives.

Ax Ilyass Moummad, Marius Miron, Lukas Rauch, David Robinson, Alexis Joly, Olivier Pietquin, Emmanuel Chemla, Matthieu Geist 4/7/2026

Audio-to-Image Bird Species Retrieval without Audio-Image Pairs via Text Distillation

Cross-modal learning for bird species recognition using audio-to-image retrieval without paired training data.

Ax Qian Wang, Xuandong Zhao, Zirui Zhang, Zhanzhi Lou, Nuo Chen, Dawn Song, Bingsheng He 4/7/2026

Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning

Training LLMs to resist cognitive biases in reasoning via reinforcement learning rather than prompting.

Ax Chenyu Yang, Denis Tarasov, Davide Liconti, Hehui Zheng, Robert K. Katzschmann 4/7/2026

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows

Dexterous robotic manipulation policy fine-tuning using diffusion models and normalizing flows for real-world scenarios.

Ax William Lugoloobi, Thomas Foster, William Bankes, Chris Russell 4/7/2026

LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations

Research on predicting LLM success from internal pre-generation activations to optimize inference efficiency in reasoning tasks.

Ax Bowen Liu, Zhi Wu, Runquan Xie, Zhanhui Kang, Jia Li 4/7/2026

Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning

SSLogic agentic meta-synthesis framework where LLM agents iteratively generate and refine task specifications for logic reasoning.

Ax Camile Lendering, Erkut Akdag, Egor Bondarev 4/7/2026

SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling

Training-free few-shot anomaly detection using subspace modeling of vision foundation model features.

Ax A. M. A. S. D. Alagiyawanna, Asoka Karunananda 4/7/2026

Noise Models Impacts and Mitigation Strategies in Photonic Quantum Machine Learning

Analysis of noise models and mitigation strategies in photonic quantum machine learning systems.

Ax Houston Haynes 4/7/2026

Adaptive Domain Models: Bayesian Evolution, Warm Rotation, and Principled Training for Geometric and Neuromorphic AI

Training framework for geometric and neuromorphic AI using alternative arithmetic substrates.

Ax Rong Fu, Jiekai Wu, Haiyun Wei, Xiaowen Ma, Shiyin Lin, Kangan Qian, Chuang Liu, Jianyuan Ni, Simon James Fong 4/7/2026

SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery

SwiftGS system for rapid 3D satellite surface reconstruction via meta-learned Gaussian primitives.

Ax Abdul Rahman 4/7/2026

CSTS: A Canonical Security Telemetry Substrate for AI-Native Cyber Detection

Canonical Security Telemetry Substrate for standardizing cybersecurity data formats for AI-driven detection.

Ax Ousmane Tom Bechir, Ad\'an Jos\'e-Garc\'ia, Zaineb Chelly Garcia, Vincent Sobanski, Clarisse Dhaenens 4/7/2026

A Firefly Algorithm for Mixed-Variable Optimization Based on Hybrid Distance Modeling

Firefly algorithm adaptation for mixed-variable optimization problems.

Ax German Sh\^ama Wache, Chaithya G R, Asma Tanabene, Sebastian Neumayer 4/7/2026

Weakly Convex Ridge Regularization for 3D Non-Cartesian MRI Reconstruction

Weakly convex ridge regularizer for 3D non-Cartesian MRI reconstruction.

Ax Michael Bidollahkhani, Freja Nordsiek, Julian M. Kunkel 4/7/2026

When GPUs Fail Quietly: Observability-Aware Early Warning Beyond Numeric Telemetry

Early warning system for GPU hardware failures using structural observability beyond numeric telemetry.

Ax Haiyue Song, Masao Utiyama 4/7/2026

OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training

OptiMer framework for optimizing data mixture ratios during continual LLM pre-training without manual tuning.

Ax Chang Sun, Rui Shi, Tsukasa Koike, Tetsuro Sekine, Akio Morita, Tetsuya Sakai 4/7/2026

Segmentation of Gray Matters and White Matters from Brain MRI data

Brain tissue segmentation from MRI using deep learning and foundation models.

Ax Hillary Mutisya, John Mugane, Gavin Nyamboga, Brian Chege, Maryruth Gathoni 4/7/2026

The Thiomi Dataset: A Large-Scale Multimodal Corpus for Low-Resource African Languages

Multimodal dataset of 601k text annotations and 385k audio recordings across 10 African languages.

Ax Kavindu Herath, Joshua Zhao, Saurabh Bagchi 4/7/2026

Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learning

Realistic backdoor attack methods for federated learning using semantically meaningful triggers.

Ax Dan Oprisa, Peter Toth 4/7/2026

Metriplector: From Field Theory to Neural Architecture

Novel neural architecture primitive based on field theory and metriplectic dynamics.

Ax Jack Young 4/7/2026

S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models

S0 tuning method for efficient LLM adaptation via state matrix optimization, outperforming LoRA on code generation tasks.

Ax Jinsu Shin, Sungeun Hong, JinYeong Bak 4/7/2026

CASHG: Context-Aware Stylized Online Handwriting Generation

Neural architecture for generating online handwriting with stroke continuity and stylistic consistency.

HN latchkey 4/7/2026

Milla-jovovich/mempalace: The highest-scoring AI memory system ever benchmarked

Stub article about mempalace AI memory system benchmark.

HN alexchen_dev 4/7/2026

OpenClaw Plugin for Claude Code CLI – Persistent Worker Pool with Smart OAuth

OpenClaw provider plugin routes LLM requests through Claude Code CLI with persistent worker pool and OAuth, enabling Claude Pro/Max access without API credentials.

HN allgrips 4/7/2026

AI workout plan generator for Indian personal trainers (coachiq.in)

LLM-based workout plan generator for personal trainers in India with WhatsApp integration and exercise library.

HN asamassekou 4/7/2026

Memory poisoning in AI coding agents

Ship Safe v7.0.0: AI-powered security platform running 19 specialized agents to scan code for vulnerabilities including LLM/agentic AI security risks.

HN m_kos 4/7/2026

Feynman: Open-source AI research agent

Open-source AI research agent that reads papers, searches web, writes drafts, runs experiments locally with cited claims.

HN gmays 4/7/2026

Fujitsu One Compression

Fujitsu One Compression is an open-source Python library for LLM post-training quantization implementing GPTQ, DBF, RTN and novel QEP methods.

HN diranged 4/7/2026

Show HN: Separating work and play in Claude Code

Claude Profile wrapper enables multiple concurrent Claude Code sessions with isolated configs per subscription (work/personal separation).

HN smissingham 4/7/2026

Show HN: Knowledge Bases for AI/Human Sharing

Knowledge base and retrieval tooling for AI-human interaction and shared memory systems.

HN h_hasegawa 4/6/2026

High AI judgment consistency does not mean high reasoning quality (preprint)

Preprint research examining judgment consistency vs reasoning quality in ChatGPT, Claude, and Gemini across 1,800 judgments.

HN evo_9 4/6/2026

OpenAI's vision for the AI economy: public wealth funds, robot taxes, and more

OpenAI policy proposals for AI economy including public wealth funds, robot taxes, and wealth redistribution mechanisms.

HN volatilityfund 4/6/2026

I use Pollinations as a lightweight LLM back end (faster than Hugging Face)

User experience comparing Pollinations as a lightweight LLM backend alternative to Hugging Face.

HN murkt 4/6/2026

Patch Claude Code system prompt to fix laziness

Node.js tool that patches Claude Code system prompts to reduce corner-cutting by rebalancing laziness/thoroughness instructions 5:1 ratio.

HN trinsic2 4/6/2026

Claude Code limits are starting to feel like a psychological trick

User complaint about Claude Code subscription limits and lack of transparency in usage metrics.

HN theaniketmaurya 4/6/2026

Open-source sandboxes to run AI code, browser agents and computer-use

SmolVM: Open-source lightweight sandboxes for running AI agent code and browser automation safely with instant boot/teardown.