Ax Jialuo Li, Wenhao Chai, Xingyu Fu, Haiyang Xu, Saining Xie 4/2/2026

Science-T2I: Addressing Scientific Illusions in Image Synthesis

ScienceT2I dataset and evaluation of image generation models for physical plausibility across 16 scientific domains.

Ax Iskander Azangulov, Peter Potaptchik, Qinyu Li, Eddie Aamari, George Deligiannidis, Judith Rousseau 4/2/2026

Adaptive Diffusion Guidance via Stochastic Optimal Control

Theoretical framework using stochastic optimal control to adaptively determine guidance weights in diffusion models.

Ax Alejandro Murillo-Gonzalez, Lantao Liu 4/2/2026

Situationally-Aware Dynamics Learning

Framework for robots to learn hidden state representations online in unstructured environments via situational awareness.

Ax Chunyang Jiang, Chi-min Chan, Yiyang Cai, Yulong Liu, Wei Xue, Yike Guo 4/2/2026

Graceful Forgetting in Generative Language Models

Addresses negative transfer in fine-tuning by selectively forgetting unhelpful pre-trained knowledge in language models.

Ax Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache 4/2/2026

Variance-Based Pruning for Accelerating and Compressing Trained Networks

Variance-based pruning method for compressing trained networks including Vision Transformers with minimal retraining.

Ax Xinfang Chen, Siyang Xiao, Xianying Zhu, Junhong Xie, Ming Liang, Dajun Chen, Wei Jiang, Yong Li, Peng Di 4/2/2026

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

NES framework for low-latency code edit suggestions without explicit instructions, using learned editing trajectories.

Ax Po-Hsien Yu, Yu-Syuan Tseng, Shao-Yi Chien 4/2/2026

FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification

Federated learning framework for person re-identification addressing non-IID data and communication efficiency.

Ax Malte L\"uken, Javier Garcia-Bernardo, Sreeparna Deb, Flavio Hafner, Megha Khosla 4/2/2026

Population-Scale Network Embeddings Expose Educational Divides in Network Structure Related to Right-Wing Populist Voting

Network embeddings on Dutch population-scale data reveal educational divides correlated with right-wing populist voting.

Ax A. Chervov, D. Fedoriaka, E. Konstantinova, A. Naumov, I. Kiselev, A. Sheveleva, I. Koltsov, S. Lytkin, A. Smolensky, A. Soibelman, F. Levkovich-Maslyuk, R. Grimov, D. Volovich, A. Isakov, A. Kostin, M. Litvinov, N. Vilkin-Krom, A. Bidzhiev, A. Krasnyi, M. Evseev, E. Geraseva, L. Grunwald, S. Galkin, E. Koldunov, S. Diner, A. Chevychelov, E. Kudasheva, A. Sychev, A. Kravchenko, Z. Kogan, A. Natyrova, L. Shishina, L. Cheldieva, V. Zamkovoy, D. Kovalenko, O. Papulov, S. Kudashev, D. Shiltsov, R. Turtayev, O. Nikitina, D. Mamayeva, S. Nikolenko, M. Obozov, A. Titarenko, A. Dolgorukova, A. Aparnev, O. Debeaupuis, S. Alami C., H. Isambert 4/2/2026

CayleyPy Growth: Efficient growth computations and hundreds of new conjectures on Cayley graphs (Brief version)

Open source CayleyPy library for efficient Cayley and Schreier graph computations, with 200+ new conjectures in group theory.

Ax Ammar Ahmed, Azal Ahmad Khan, Ayaan Ahmad, Sheng Di, Zirui Liu, Ali Anwar 4/2/2026

Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts

Retrieval-of-Thought (RoT) system reuses prior reasoning steps organized in thought graphs to improve LLM inference efficiency.

Ax Boxuan Zhang, Yi Yu, Jiaxuan Guo, Jing Shao 4/2/2026

Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents

Evaluates self-replication risks in LLM agents through realistic testing of autonomous agent behaviors and safety concerns.

Ax Samar Fares, Nurbek Tastan, Noor Hussein, Karthik Nandakumar 4/2/2026

MOLM: Mixture of LoRA Markers

Watermarking method (MOLM) for detecting and attributing synthetically generated images using LoRA markers.

Ax Yuanfang Xiang, Lun Ai 4/2/2026

Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction

Framework integrating data-driven learning with knowledge bases for genetic perturbation prediction in cellular systems.

Ax Shira Schiber, Ofir Lindenbaum, Idan Schwartz 4/2/2026

TempoControl: Temporal Attention Guidance for Text-to-Video Models

TempoControl method for fine-grained temporal control in text-to-video generation models.

Ax Amitis Shidani, Tyler Farghly, Yang Sun, Habib Ganjgahi, George Deligiannidis 4/2/2026

Beyond Real Data: Synthetic Data through the Lens of Regularization

Learning-theoretic framework quantifying trade-offs between synthetic and real data using algorithmic stability bounds.

Ax Percy S. Zhai, So Won Jeong, Veronika Ro\v{c}kov\'a 4/2/2026

Conditional Flow Matching for Bayesian Posterior Inference

Proposes flow matching method for Bayesian posterior inference without likelihood evaluation, using block-triangular velocity fields.

Ax Mykolas Sveistrys, Richard Kunert 4/2/2026

PluriHopRAG: Exhaustive, Recall-Sensitive QA Through Corpus-Specific Document Structure Learning

RAG system for exhaustive multi-document question answering that checks all relevant documents without clear stopping conditions.

Ax Veranika Boukun, J\"org L\"ucke 4/2/2026

Disentanglement of Sources in a Multi-Stream Variational Autoencoder

Multi-Stream VAE architecture combining discrete and continuous latent spaces for disentangled representation learning.

Ax Elias Hossain, Mehrdad Shoeibi, Ivan Garibay, Niloofar Yousefi 4/2/2026

BIOGEN: Evidence-Grounded Multi-Agent Reasoning Framework for Transcriptomic Interpretation in Antimicrobial Resistance

Multi-agent reasoning framework using AI agents for interpreting gene clusters in antimicrobial resistance transcriptomic data.

Ax Guneet S. Dhillon, Javier Gonz\'alez, Teodora Pandeva, Alicia Curth 4/2/2026

E-Scores for (In)Correctness Assessment of Generative Model Outputs

Framework using conformal prediction to assess correctness of LLM outputs and construct confidence sets for generative model responses.

Ax Wenlun Zhang, Yunshan Zhong, Zihao Ding, Xinyu Li, Kentaro Yoshioka 4/2/2026

D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models

Data-free quantization techniques for CLIP vision-language models enabling model compression without real data access for privacy-sensitive scenarios.

Ax Asad Aali, Muhammad Ahmed Mohsin, Vasiliki Bikia, Arnav Singhvi, Richard Gaus, Suhana Bedi, Hejie Cui, Miguel Fuentes, Alyssa Unell, Yifan Mai, Jordan Cahoon, Michael Pfeffer, Roxana Daneshjou, Sanmi Koyejo, Emily Alsentzer, Christopher Potts, Nigam H. Shah, Akshay S. Chaudhari 4/2/2026

Structured Prompts Improve Evaluation of Language Models

Study showing structured prompts significantly improve language model evaluation accuracy compared to single static prompt configurations in benchmarking.

Ax Yuexin Xiang, Yuchen Lei, Yuanzhe Zhang, Qin Wang, Tsz Hon Yuen, Andreas Deppeler, Jiangshan Yu 4/2/2026

Leveraging Large Language Models to Bridge Cross-Domain Transparency in Stablecoins

LLM-based framework bridging cross-domain data sources for stablecoin transparency in circulation, reserves, and disclosure records.

Ax Kehlani Fay, Darin Anthony Djapri, Anya Zorin, James Clinton, Ali El Lahib, Hao Su, Michael T. Tolley, Sha Yi, Xiaolong Wang 4/2/2026

House of Dextra: Cross-embodied Co-design for Dexterous Hands

Co-design framework for learning task-specific robot hand morphology and dexterous control policies simultaneously.

Ax Weifan Guan, Qinghao Hu, Huasen Xi, Chenxiao Zhang, Aosheng Li, Jian Cheng 4/2/2026

RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI

RoboNeuron middleware layer connecting Vision-Language-Action models and LLM agents to robot middleware, standardizing tool API integration for embodied AI.

Ax Samar Fares, Nurbek Tastan, Karthik Nandakumar 4/2/2026

SPDMark: Selective Parameter Displacement for Robust Video Watermarking

SPDMark framework for robust in-generation video watermarking balancing imperceptibility, robustness, and computational efficiency.

Ax Jan Tagscherer, Sarah de Boer, Lena Philipp, Fennie van der Graaf, Dr\'e Peeters, Joeran Bosma, Lars Leijten, Bogdan Obreja, Ewoud Smit, Alessa Hering 4/2/2026

EvalBlocks: A Modular Pipeline for Rapidly Evaluating Foundation Models in Medical Imaging

EvalBlocks modular framework for efficient evaluation of foundation models in medical imaging, reducing manual experiment tracking workflows.

Ax Lucas Kook, S{\o}ren Wengel Mogensen 4/2/2026

Exact Graph Learning via Integer Programming

Graph learning via integer programming for causal discovery and inferring dependence structures in complex systems without restrictive assumptions.

Ax Bj\"orn Hoppmann, Christoph Scholz 4/2/2026

Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent

Survey of meta-learning and meta-reinforcement learning methods enabling rapid task adaptation with minimal data, tracing DeepMind's adaptive agent research.

Ax Haoyang Fang, Shuai Zhang, Yifei Ma, Hengyi Wang, Cuixiong Hu, Katrin Kirchhoff, Bernie Wang, George Karypis 4/2/2026

OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation

OPERA data pruning framework for efficient dense retriever adaptation, balancing quality-coverage tradeoff in domain-specific finetuning.

Ax Ishrith Gowda, Chunwei Liu 4/2/2026

SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization

Self-attention CycleGAN for multi-site MRI harmonization addressing scanner-induced covariate shifts in neuroimaging data.

Ax Eric A. Moreno, Samuel Bright-Thonney, Andrzej Novak, Dolores Garcia, Philip Harris 4/2/2026

AI Agents Can Already Autonomously Perform Experimental High Energy Physics

AI agents autonomously perform high energy physics analysis pipeline stages including event selection, background estimation, and statistical inference using LLMs.

Ax Tanay Varshney, Annie Surla, Michelle Xu, Gomathy Venkata Krishnan, Maximilian Jeblick, David Austin, Neal Vaidya, Davide Onofrio 4/2/2026

LLM Router: Rethinking Routing with Prefill Activations

LLM Router uses internal prefill activations for query-specific model selection, outperforming semantic routing by capturing model-specific failures.

Ax Brianna Binder, Agnimitra Dasgupta, Assad Oberai 4/2/2026

Closed-form conditional diffusion models for data assimilation

Closed-form conditional diffusion models for data assimilation using analytical score functions instead of neural network approximations.

Ax Jiahua Liu, Benchong Li 4/2/2026

The No-Clash Teaching Dimension is Bounded by VC Dimension

Theoretical proof that No-Clash Teaching Dimension is bounded by VC Dimension in machine learning theory.

Ax Guilin Zhang, Wulan Guo, Ziqi Tan, Chuanyi Sun, Hailong Jiang 4/2/2026

CarbonEdge: Carbon-Aware Deep Learning Inference Framework for Sustainable Edge Computing

CarbonEdge framework for carbon-aware deep learning inference on edge devices, optimizing for environmental impact alongside latency and throughput.

Ax Rishi Rani, Massimo Franceschetti 4/2/2026

Fundamental Limits of Man-in-the-Middle Attack Detection in Model-Free Reinforcement Learning

Theoretical analysis of man-in-the-middle attack detection in model-free reinforcement learning systems using Bellman Deviation Detection framework.

Ax Sean Disar\`o, Ruma Rani Maity, Aras Bacho 4/2/2026

Deflation-PINNs: Learning Multiple Solutions for PDEs and Landau-de Gennes

Physics-Informed Neural Networks framework (Deflation-PINNs) for solving nonlinear PDEs by identifying multiple distinct solutions using deflation loss.

HN duozokker 4/2/2026

Show HN: Agent2; Open-source production runtime for AI agents

Agent2 open-source runtime for production AI agents with schema-to-API capabilities, auth, and provider routing.

HN OnTheFlyJOINs 4/2/2026

Why Your Database Optimizer Matters More When AI Writes the Queries

Database optimizers become critical infrastructure when AI agents autonomously generate SQL queries.

HN joaoli131 4/2/2026

Show HN: Semantic atlas of 188 constitutions in 3D (30k articles, embeddings)

3D semantic atlas of 188 constitutions using embeddings and UMAP for conceptual law search.

HN SanjayMehta 4/2/2026

The reputation of troubled YC startup Delve has gotten worse

YC startup Delve faces whistleblower allegations of misusing open source code without attribution.

HN kevinlu 4/2/2026

Show HN: Hybro – unify local and remote AI agents in a single agent network

Hybro interoperability layer enables local and remote AI agents to coordinate in shared networks.

HN kristianp 4/2/2026

Arcee-AI Trinity-Large-Thinking

Trinity-Large-Thinking 398B sparse MoE model with chain-of-thought reasoning and agentic RL.

HN kristianp 4/2/2026

Trinity Large Thinking

Trinity Large Thinking open-source reasoning model from Arcee AI optimized for agentic tasks.

HN txtsd 4/2/2026

Ask HN: Is there any interest in a native Qt/C++ Discord client?

Developer building native Qt/C++ Discord client as alternative to Electron-based apps.

HN saligne 4/2/2026

MCP Server turned my NAS into a self-hosted AI assistant

Tutorial using Model Context Protocol server to turn NAS into self-hosted AI assistant.

HN walterbell 4/2/2026

Organizations Using AI Are Confusing Temporary Friction with Permanent Safety

Analysis of AI adoption risks: organizations mistaking temporary model limitations for safety assurance.

HN measurablefunc 4/2/2026

Mercor AI Breached via LiteLLM

Brief mention of Mercor AI breach related to LiteLLM library.

HN 0x1997 4/2/2026

Claude Code Cache Bug Analysis

Analysis of two cache bugs in Claude Code API causing 10-20x token inflation and rapid rate limit exhaustion. Includes technical details and community-documented workarounds.