Ax Janaka Chathuranga Brahmanage, Akshat Kumar 4/1/2026

Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning

Safety-aware offline RL method using budget-conditioned reachability analysis for constrained decision-making.

Ax YanZhao Zheng, ZhenTao Zhang, Chao Ma, YuanQiang Yu, JiHuai Zhu, Yong Wu, Tianze Xu, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu 4/1/2026

SkillRouter: Skill Routing for LLM Agents at Scale

SkillRouter: System for routing LLM agent requests to relevant skills from large skill libraries at inference time.

Ax Edward J. Yoon 4/1/2026

ITQ3_S: High-Fidelity 3-bit LLM Inference via Interleaved Ternary Quantization with Rotation-Domain Smoothing

ITQ3_S: 3-bit LLM quantization method using interleaved ternary quantization and rotation-domain smoothing for efficient inference.

Ax Bodla Krishna Vamshi, Haizhao Yang 4/1/2026

Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning

Interpretability method for reinforcement learning using principal prototype analysis on manifolds.

Ax Manyi Yao, Abhishek Aich, Yumin Suh, Amit Roy-Chowdhury, Christian Shelton, Manmohan Chandraker 4/1/2026

Image-Specific Adaptation of Transformer Encoders for Compute-Efficient Segmentation

Vision transformer optimization for image segmentation with adaptive computation per input image.

Ax Hannes Kunstmann, Joseph Ollier, Joel Persson, Florian von Wangenheim 4/1/2026

EventChat: Implementation and user-centric evaluation of a large language model-driven conversational recommender system for exploring leisure events in an SME context

LLM-driven conversational recommender system for leisure event discovery with user-centric evaluation in SME context.

Ax Pablo Hern\'andez-C\'amara, Jorge Vila-Tom\'as, Paula Dauden-Oliver, Nuria Alabau-Bosque, Valero Laparra, Jes\'us Malo 4/1/2026

Image Segmentation via Divisive Normalization: dealing with environmental diversity

Image segmentation approach using divisive normalization for autonomous driving under diverse environmental conditions.

Ax Pablo Carrasco, Gonzalo Mu\~noz 4/1/2026

Tightening convex relaxations of trained neural networks: a unified approach for convex and S-shaped activations

Framework for tightening convex relaxations of trained neural networks with convex and S-shaped activations for optimization incorporation.

Ax Marco Moletta, Michael C. Welle, Nils Ingelhag, Jesper Munkeby, Danica Kragic 4/1/2026

Real-Time Operator Takeover for Visuomotor Diffusion Policy Training

Real-time operator takeover paradigm allowing seamless human intervention and correction during visuomotor diffusion policy execution.

Ax Thomas F Burns, Letitia Parcalabescu, Stephan W\"aldchen, Michael Barlow, Gregor Ziegltrum, Volker Stampa, Bastian Harren, Bj\"orn Deiseroth 4/1/2026

Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation

German-language LLM pre-training dataset curated via heuristic filtering, model-based selection, and synthetic data generation.

Ax Hengzhe Zhang, Qi Chen, Bing Xue, Wolfgang Banzhaf, Mengjie Zhang 4/1/2026

LLM-Meta-SR: In-Context Learning for Evolving Selection Operators in Symbolic Regression

Meta-learning framework using LLMs to automatically design selection operators for evolutionary symbolic regression algorithms.

Ax Zheda Mai, Arpita Chowdhury, Zihe Wang, Sooyoung Jeon, Lemeng Wang, Jiacheng Hou, Wei-Lun Chao 4/1/2026

AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models

AVA-Bench systematically evaluates atomic visual abilities of vision foundation models independent of LLM instruction tuning.

Ax Qingyan Wei, Yaojie Zhang, Zhiyuan Liu, Puyu Zeng, Yuxuan Wang, Biqing Qi, Dongrui Liu, Linfeng Zhang 4/1/2026

Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles

SlowFast Sampling optimizes inference efficiency in diffusion-based language models through dynamic, flexible token generation strategies.

Ax Dong Zhuo, Wenzhao Zheng, Jiahe Guo, Yuqi Wu, Jie Zhou, Jiwen Lu 4/1/2026

Streaming 4D Visual Geometry Transformer

Streaming transformer architecture inspired by autoregressive LLMs for real-time 3D geometry perception and reconstruction from video.

Ax Xinfang Chen, Siyang Xiao, Xianying Zhu, Junhong Xie, Ming Liang, Dajun Chen, Wei Jiang, Yong Li, Peng Di 4/1/2026

NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories

NES is an instruction-free code editing framework that learns from historical editing trajectories to suggest next edits with low latency.

Ax Dongjae Jeon, Taeheon Kim, Seongwon Cho, Minhyuk Seo, Jonghyun Choi 4/1/2026

TTA-DAME: Test-Time Adaptation with Domain Augmentation and Model Ensemble for Dynamic Driving Conditions

Test-time adaptation method using domain augmentation and model ensembles to handle weather-related domain shifts in autonomous driving.

Ax Taeheon Kim, San Kim, Minhyuk Seo, Dongjae Jeon, Wonje Jeung, Jonghyun Choi 4/1/2026

Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning

Knowledge distillation and self-supervised learning approach for continual learning with class-incremental learning and external unlabeled data.

Ax Nitin Gupta, Bapi Dutta, Anupam Yadav 4/1/2026

A Machine Learning Based Explainability Framework for Interpreting Swarm Intelligence

Interpretability framework for understanding how components of particle swarm optimization algorithms affect performance.

Ax Zhaoyang Li, Zhan Ling, Yuchen Zhou, Litian Gong, Erdem B{\i}y{\i}k, Hao Su 4/1/2026

ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models

Benchmark evaluating how large vision-language models handle object recognition in contextually incongruent scenes and manage uncertainty.

Ax Yixuan Wang, Huang He, Siqi Bao, Hua Wu, Haifeng Wang, Qingfu Zhu, Wanxiang Che 4/1/2026

ProxyAttn: Guided Sparse Attention via Representative Heads

ProxyAttn method using representative attention heads to enable efficient sparse attention in LLMs for long-text processing with minimal performance degradation.

Ax Jan Ole von Hartz, Lukas Schweizer, Joschka Boedecker, Abhinav Valada 4/1/2026

MSG: Multi-Stream Generative Policies for Sample-Efficient Robotic Manipulation

Multi-Stream Generative Policy framework for robot learning that combines multiple object-centric policies at inference to improve sample efficiency and generalization.

Ax Emanuele Marconato, Samuele Bortolotti, Emile van Krieken, Paolo Morettin, Elena Umili, Antonio Vergari, Efthymia Tsamoura, Andrea Passerini, Stefano Teso 4/1/2026

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts

Neuro-symbolic AI overview connecting neural networks with symbolic reasoning to satisfy constraints, addressing reliable trustworthy AI development.

Ax M\'aty\'as Schubert, Tom Claassen, Sara Magliacane 4/1/2026

Local Causal Discovery for Statistically Efficient Causal Inference

Efficient local causal discovery method for identifying adjustment sets without learning the full causal graph.

Ax Weiqi Li, Quande Zhang, Ruifeng Zhai, Liang Lin, Guangrun Wang 4/1/2026

VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling

One-shot adaptation framework improving vision-language-action model generalization to novel camera viewpoints through spatial representation recalibration.

Ax Manurag Khullar, Utkarsh Desai, Poorva Malviya, Aman Dalmia, Zheyuan Ryan Shi 4/1/2026

Script Gap: Evaluating LLM Triage on Indian Languages in Native vs Romanized Scripts in a Real World Setting

Evaluation of LLM performance on Indian language maternal healthcare triage, comparing native scripts versus romanized text in real-world deployment.

Ax Xingyu Zhou, Qifan Li, Xiaobin Hu, Hai Chen, Shuhang Gu 4/1/2026

Guiding a Diffusion Transformer with the Internal Dynamics of Itself

Guidance strategy for diffusion transformers using internal model dynamics to improve image generation quality without external classifiers.

Ax Samuel Cyrenius Anderson 4/1/2026

The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models

Analysis of 25k chain-of-thought trajectories showing neural scaling triggers domain-specific phase transitions in reasoning rather than uniform capability improvements across 8B-70B parameter models.

Ax Yi-Kai Zhang, Zhiyuan Yao, Hongyan Hao, Yueqing Sun, Qi Gu, Hui Su, Xunliang Cai, De-Chuan Zhan, Han-Jia Ye 4/1/2026

$V_0$: A Generalist Value Model for Any Policy at State Zero

V0 is a generalist value model for policy gradient methods that scales efficiently with LLM training, replacing large critic models in actor-critic methods like PPO.

Ax Zachary Bamberger, Till R. Saenger, Gilad Morad, Ofra Amir, Brandon M. Stewart, Amir Feder 4/1/2026

STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts

STATe presents an interpretable inference-time-compute method using structured action templates to improve output diversity and reasoning control in tree-of-thoughts approaches for LLMs.

Ax Wisdom Ikezogwo, Mehmet Saygin Seyfioglu, Ranjay Krishna, Karim Bouyarmane 4/1/2026

When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On

Error enumeration as reward signal for reference-free RL post-training in virtual try-on with multiple valid outputs.

Ax Dharshan Kumaran, Arthur Conmy, Federico Barbero, Simon Osindero, Viorica Patraucean, Petar Velickovic 4/1/2026

How do LLMs Compute Verbal Confidence

Study investigating how LLMs compute verbal confidence: timing of computation and relationship to answer quality.

Ax Hui Wen Goh, Jonas Mueller 4/1/2026

Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction

CONSTRUCT: real-time uncertainty estimator for LLM structured outputs and data extraction with field-level trustworthiness scoring.

Ax Zhi Sun, Wenming Zhang, Yi Wei, Liren Yu, Zhixuan Zhang, Dan Ou, Haihong Tang 4/1/2026

KARMA: Knowledge-Action Regularized Multimodal Alignment for Personalized Search at Taobao

KARMA: fine-tuning LLMs for e-commerce personalized search via knowledge-action regularization addressing semantic-behavior gaps.

Ax Toluwani Aremu, Daniil Ognev, Samuele Poppi, Nils Lukas 4/1/2026

Robust Safety Monitoring of Language Models via Activation Watermarking

Activation watermarking technique for detecting adaptive adversarial attacks against LLMs during inference monitoring.

Ax In-Chang Baek, Jiyun Jung, Geum-Hwan Hwang, Sung-Hyun Kim, Kyung-Joong Kim 4/1/2026

Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation

Language-conditioned multi-game level generation via shared representation learning across multiple game domains.

Ax Lorcan McLaren, James Cross, Zuzanna Krakowska, Robin Rauner, Martijn Schoonvelde 4/1/2026

Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation

Controlled study comparing LLM model choice, size, and prompt styles for political text annotation; challenges best practices.

Ax Julio C. Serrano, Joonas Kevari, Rumy Narayan 4/1/2026

A Multi-Agent Rhizomatic Pipeline for Non-Linear Literature Analysis

Multi-agent pipeline for non-linear literature analysis using rhizomatic approach grounded in process-relational ontology.

HN SPLLC 4/1/2026

We built an O(1) KV Cache for LLMs (Qwen2.5-7B Colab inside)

O(1) KV Cache optimization for LLMs with Qwen2.5-7B implementation example in Colab.

HN koito17 4/1/2026

Tell HN: Zed is sunsetting text threads

Zed code editor sunsetting Text Threads feature in favor of maturing Agent Panel with tool use and agentic capabilities.

HN celestix 4/1/2026

Induced-Fit Retrieval: A 1958 biochemistry concept beats RAG at multi-hop

Induced-Fit Retrieval: Dynamic graph-traversal RAG system mutating queries at each hop based on retrieved documents, improving multi-hop reasoning over static RAG.

HN miacycle 4/1/2026

Anthropic open sourced Claude Code

Brief mention of Anthropic open-sourcing Claude Code with no technical details provided.

HN handfuloflight 4/1/2026

AI Agent Traps

Guide on building, training and deploying AI agents. Limited technical depth in provided excerpt.

HN matt_d 4/1/2026

Rethinking Language Model Scaling Under Transferable Hypersphere Optimization

Research on language model scaling using transferable hypersphere optimization techniques for improved training efficiency.

HN jbarrow 4/1/2026

LFM2.5-350M: No Size Left Behind

LFM2.5-350M model released with 28T token pre-training, optimized for inference on CPUs and GPUs with tool use capabilities.

HN phwbikm 4/1/2026

Crypto Investment Management Claude Skill

Claude Code skill suite for crypto investment management demonstrating multi-agent system patterns.

HN latentlie_747 4/1/2026

DefenseClaw: Secure Your OpenClaw

Enterprise governance layer for OpenClaw agents providing security controls for skills, MCP servers, and code execution.

HN shenli3514 4/1/2026

How Claude Code memory works

Explanation of how Claude Code memory system persists project context across sessions using disk-based file loading.

HN jwilliams 4/1/2026

Early Observations from Interviews with Engineering Teams Adopting AI

Analysis of engineering teams successfully adopting AI coding tools; workflow patterns identified.

HN wontopos 4/1/2026

Show HN: WMB-100K – Open benchmark for AI memory systems at 100K turns

WMB-100K: Enterprise benchmark for AI memory systems with 4.3M tokens, 2,708 questions, 100K turns.

HN viftode4 4/1/2026

Show HN: Live simulation of AI agents scamming each other (and getting caught)

Live simulation showing AI agents scamming each other; demonstrates trust and verification gaps in agent economies.