Ax Ziang Song, Ying Jin, Emmanuel J. Cand\`es 28d ago

Everywhere Valid Bounds on False Discovery Proportions in Conformal Inference

Statistical method for controlling false discovery proportions in conformal inference for multiple testing problems.

Ax Mouhamed Amine Bouchiha, Abdelaziz Amara Korba, Yacine Ghamri-Doudane 28d ago

Automated Byzantine-Resilient Clustered Decentralized Federated Learning for Battery Intelligence in Connected EVs

Federated learning framework for EV battery management with Byzantine-resilient decentralized aggregation for privacy-preserving anomaly detection.

Ax Yingxue Zhao, Haoran Li, Haosu Zhou, Tobias Pfaff, Nan Li 28d ago

A finite-element-inspired bipartite graph learned simulator for manufacturability assessment in large-deformation sheet forming

Graph neural network learned simulator for finite element sheet forming analysis, approximating FE state transitions for design optimization.

Ax Franka Bause, Jonas Niederle, Martin Pawelczyk, Rebekka Burkholz 28d ago

Multi-Agent Systems are Mixtures of Experts: Who Becomes an Influencer?

Analysis of multi-agent LLM deliberation through Friedkin-Johnsen opinion dynamics, modeling influence and collaboration patterns between agents.

Ax Pongpisit Thanasutives, Naichang Ke, Yoshinobu Kawahara 28d ago

Data-driven sparse identification of governing PDEs via knockoff filters and multi-criteria trade-offs

KO-PDE-IDENT: data-driven framework for discovering parsimonious PDEs from noisy observations using knockoff filters and false discovery rate control.

Ax NVIDIA, :, Aditi, Niket Agarwal, Arslan Ali, Jon Allen, Martin Antolini, Adeline Aubame, Alisson Azzolini, Junjie Bai, Maciej Bala, Yogesh Balaji, Josh Bapst, Aarti Basant, Mukesh Beladiya, Mohammad Qazim Bhat, Zaid Pervaiz Bhat, Dan Blick, Vanni Brighella, Han Cai, Tiffany Cai, Eric Cameracci, Jiaxin Cao, Yulong Cao, Mark Carlson, Carlos Casanova, Ting-Yun Chang, Yan Chang, Yu-Wei Chao, Prithvijit Chattopadhyay, Roshan Chaudhari, Chieh-Yun Chen, Junyu Chen, Ke Chen, Qizhi Chen, Wenkai Chen, Xiaotong Chen, Yu Chen, An-Chieh Cheng, Click Cheng, Xiu Chia, Jeana Choi, Chaeyeon Chung, Wenyan Cong, Yin Cui, Magdalena Dadela, Nalin Dadhich, Wenliang Dai, Joyjit Daw, Alperen Degirmenci, Rodrigo Vieira Del Monte, Robert Denomme, Sameer Dharur, Marco Di Lucca, Ke Ding, Wenhao Ding, Yifan Ding, Yuzhu Dong, Nicole Drumheller, Yilun Du, Aigul Dzhumamuratova, Aleksandr Efitorov, Hamid Eghbalzadeh, Naomi Eigbe, Imad El Hanafi, Hassan Eslami, Benedikt Falk, Jiaojiao Fan, Jim Fan, Amol Fasale, Sergiy Fefilatyev, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Vikram Fugro, Prashant Gaikwad, TJ Galda, Katelyn Gao, Yihuai Gao, Wenhang Ge, Sreyan Ghosh, Arushi Goel, Vivek Goel, Akash Gokul, Rama Govindaraju, Jinwei Gu, Miguel Guerrero, Elfie Guo, Aryaman Gupta, Siddharth Gururani, Hugo Hadfield, Song Han, Ankur Handa, Zekun Hao, Mohammad Harrim, Ali Hassani, Nathan Hayes-Roth, Yufan He, Chris Helvig, Cyrus Hogg, Madison Huang, Michael Huang, Sophia Huang, Yufan Huang, Jacob Huffman, DeLesley Hutchins, Suneel Indupuru, Boris Ivanovic, Arihant Jain, Joel Jang, Ryan Ji, Yanan Jian, Dongfu Jiang, Jingyi Jin, Atharva Joshi, Nikhilesh Joshi, Pranjali Joshi, Andy Ju, Jaehun Jung, Weiwei Kang, Scott Kassekert, Jan Kautz, Ashna Khetan, Julia Kiczka, Slawek Kierat, Gwanghyun Kim, Kuno Kim, Sunny Kim, Kezhi Kong, Xin Kong, Zhifeng Kong, Tomasz Kornuta, Egor Krivov, Hui Kuang, Saurav Kumar, Chia-Wen Kuo, George Kurian, Wojciech Kutak, JF Lafleche, Himangshu Lahkar, Omar Laymoun, Jayjun Lee, Sanggil Lee, Gabriele Leone, Boyi Li, Freya Li, Jiajun Li, Jinfeng Li, Ling Li, Pengcheng Li, Shangru Li, Tingle Li, Xiaolong Li, Xuan Li, Zhaoshuo Li, Zhiqi Li, Hao Liang, Maosheng Liao, Chen-Hsuan Lin, Tsung-Yi Lin, Ming-Yu Liu, Sifei Liu, Zihan Liu, Hai Loc Lu, Xiangyu Lu, Alice Luo, Ruipu Luo, Wenjie Luo, Jiangran Lyu, Martin Ding Ma, Nic Ma, Qianli Ma, Dawid Majchrowski, Louis Marcoux, Miguel Martin, Qing Miao, Ashkan Mirzaei, Shreyas Misra, Kaichun Mo, Durra Mohsin, Hyejin Moon, Pawel Morkisz, Saeid Motiian, Kirill Motkov, Seungjun Nah, Yashraj Narang, Deepak Narayanan, Thabang Ngazimbi, Julian Ouyang, Shubham Pachori, David Page, Yatian Pang, Sehwi Park, Mahesh Patekar, Mostofa Patwary, Marco Pavone, Trung Pham, Wei Ping, Soha Pouya, Shrimai Prabhumoye, Varun Praveen, Delin Qu, Hesam Rabeti, Morteza Ramezanali, Marilyn Reeb, Xuanchi Ren, Kristen Rumley, Wojciech Rymer, Jun Saito, Yeongho Seol, John Shao, Piyush Shekdar, Tianwei Shen, Humphrey Shi, Min Shi, Stella Shi, Kevin Shih, Mohammad Shoeybi, Mateusz Sieniawski, Shuran Song, Alexander Sotelo, Amir Sotoodeh, Sunil Srinivasa, Vignesh Srinivasakumar, Bartosz Stefaniak, Rahul Heinrich Steiger, Shangkun Sun, Jiaxiang Tang, Shitao Tang, Yangyang Tang, Yue Tang, Tolou Tavakkoli, Kayley Ting, Krzysztof Tomala, Wei-Cheng Tseng, Jibin Varghese, Sergei Vasilev, Thomas Volk, Raju Wagwani, Roger Waleffe, Andrew Z. Wang, Boxiang Wang, Haoxiang Wang, Qiao Wang, Shihao Wang, Shijie Wang, Ting-Chun Wang, Yan Wang, Yu Wang, Rohit Watve, David Wehr, Fangyin Wei, Xinshuo Weng, Jay Zhangjie Wu, Kedi Wu, Hongchi Xia, Summer Xiao, Tianjun Xiao, Kevin Xie, Daguang Xu, Jiashu Xu, Mengyao Xu, Ruqing Xu, Xingqian Xu, Yao Xu, Dinghao Yang, Dong Yang, Hans Yang, Xiaodong Yang, Xuning Yang, Yichu Yang, Yurong You, Zhiding Yu, Hao Yuan, Simon Yuen, Xiaohui Zeng, Pengcuo Zeren, Cindy Zha, Haotian Zhang, Jenny Zhang, Jing Zhang, Liangkai Zhang, Paris Zhang, Shun Zhang, Xuanmeng Zhang, Zhizheng Zhang, Ann Zhao, Yilin Zhao, Yuliya Zhautouskaya, Charles Zhou, Fengzhe Zhou, Shilin Zhu, Yuke Zhu, Dima Zhylko, Artur Zolkowski 28d ago

Cosmos 3: Omnimodal World Models for Physical AI

Cosmos 3: omnimodal foundation models for Physical AI using mixture-of-transformers architecture processing language, vision, video, audio, and actions.

Ax Wenyu Liao, Yiqing Shi, Fang Xie 28d ago

Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks

Knockoff-based false discovery rate control method for feature selection and simplification in deep neural networks.

Ax Eric Spencer, Arslan Bisharat, Brian Ortiz, Khushboo Bhadauria, TaiNing Wang, George K. Thiruvathukal, Konstantin Laufer, Mohammed Abuhamad 28d ago

TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation

TLA-Prover: 20B parameter LLM fine-tuned for verifiable TLA+ distributed systems specification synthesis with supervised learning and preference optimization.

Ax Maciej Wielgosz, Stefano Puliti, Rasmus Astrup 28d ago

SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests

SegmentAnyTreeV2 transformer-based framework for semantic and instance segmentation of forest point clouds across multiple sensors and platforms.

Ax Omid Ahmadieh, Nima Karimian 28d ago

Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attacks

Generative adversarial attack framework using diffusion models with LoRA fine-tuning to synthesize adversarial faces for facial recognition systems.

Ax Yash Vardhan Tomar, Dheeraj Peddireddy 28d ago

Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing

Graph reinforcement learning approach for quantum circuit routing using calibration-aware policies trained with proximal policy optimization.

Ax Aleksandr Tsymbalov, Danis Zaripov, Artem Epifanov, Anastasiya Palienko 28d ago

GRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science

GRACE-DS: evaluation environment for LLM-powered AutoML agents on tabular data tasks, covering planning through validation and model deployment.

Ax Sunwoo Kim, Sunkyung Lee, Clark Mingxuan Ju, Donald Loveland, Bhuvesh Kumar, Kijung Shin, Neil Shah, Liam Collins 28d ago

On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies

Study of memorization behavior in LLM-based generative recommendation systems with training strategies to improve generalization beyond pattern memorization.

Ax Gaurav Gupta, Vatshank Chaturvedi, Jun Huan, Anoop Deoras 28d ago

Dissecting model behavior through agent trajectories

Research on intent-execution gap in AI agents, analyzing how model capabilities are realized through agent system harnesses via trajectory analysis.

Ax Haoqi Yuan, Zhixuan Liang, Anzhe Chen, Ye Wang, Haoyang Li, Pei Lin, Yiyang Huang, Zixing Lei, Tong Zhang, Jiazhao Zhang, Jie Zhang, Jingyang Fan, Gengze Zhou, Qihang Peng, Chenxu Lv, Xiaoyue Chen, An Yang, Fei Huang, Junyang Lin, Dayiheng Liu, Jingren Zhou, Chenfei Wu, Xiong-Hui Chen 28d ago

Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

Qwen-RobotManip applies foundation model scaling and alignment techniques to robotic manipulation tasks with heterogeneous training data.

Ax Longlong Zhu, Jiashuo Yu, Zedi Chen, Yuhan Wu, Zhifan Jiang, Yuchen Xian, Yimeng Liu, Jiajie Su, Shaopeng Zhou, Xingyuan Li, Hongyan Liu, Xuan Liu, Dong Zhang, Chunming Wu, Xiang Chen 28d ago

OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization

OmniPlan framework optimizes network planning across transportation, communication, and power grids using MIP solvers, heuristics, and deep reinforcement learning.

HN polynomial 28d ago

Treating Agent Reasoning as a Span

Agent reasoning as observability/trust framework. Discusses production deployment challenges for autonomous agents with write access.

HN notanaiagent 28d ago

Show HN: Righthand – Autonomous AI assistants with skills, goals, and a CLI

Righthand: autonomous AI agents with persistent identity, memory, and CLI integration that operate within workflows rather than reactive prompts.

HN ricardo-larosa 28d ago

HandoffKit: Coordinate agents by passing messages, not sharing memory

HandoffKit: Open-source OpenAI plugin coordinating multiple coding agents via message passing instead of shared memory.

HN rheorix 28d ago

A Chrome extension for AI routing that reduces friction when selecting AI models

PromptRouter: Chrome extension that routes prompts to most suitable AI assistant based on request type.

HN mengk 28d ago

A framework for verifiable analysis of AI behavior

Framework for verifiable analysis of AI agent behavior tracking strategy changes, reward hacking, and performance regressions during training.

HN toluwajibodu 28d ago

Show HN: Reyn – local-first AI that journals and recalls your work

Reyn: Local-first AI tool for capturing and recalling work context via screen recording with granular privacy filters.

HN rusackas 28d ago

Localtalk: A Mac app using local WisprKit, to talk to your computer PRIVATELY

Localtalk: macOS app for private local speech-to-text using Whisper model, no cloud storage.

HN NWChen 28d ago

Universal Manipulation Exoskeleton

Universal Manipulation Exoskeleton: Hardware for collecting force/torque feedback data to train compliant robotic manipulation policies.

HN developaaah 28d ago

PGP Manager – A user-friendly approach to PGP

PGP Manager: Cross-platform desktop application for OpenPGP key management and encryption with modern UX.

HN Bender 28d ago

Linux 7.2 Slab Changes Include More Performance Optimizations

Linux 7.2 kernel slab memory allocator performance improvements.

HN dttdrv 28d ago

Show HN: OptiSYS – an open source Windows optimizer that isn't snake oil

OptiSYS: Open-source Windows PC optimizer tool with one-click setup.

HN driftguard 28d ago

ToolSchema Kit – reproducible MCP contract drift lab (10-min tutorial)

ToolSchema Kit: MCP contract testing framework for detecting tool schema drift in agent platforms like Cursor and Claude Desktop.

HN mattsadowsky 28d ago

Ask HN: How to deal with UI within the agentic loop

Discussion thread asking for UI rendering approaches within agentic LLM chat loops for SaaS.

HN recroad 28d ago

Model Card: unsloth/GLM-5.2-GGUF

Model card for GLM-5.2-GGUF quantized model. Usage examples across multiple inference frameworks and tools.

HN daxaur 28d ago

Show HN: Tabia – The first free, open-source chess opening trainer

Tabia: Open-source browser-based chess opening trainer using chess.js and Stockfish-WASM, no account required.

HN rhuber 28d ago

ASK HN: AI models are built on all of us, should their weights act like patents?

Discussion: Should AI model weights be treated similarly to patents given they compress collective human knowledge?

HN sawyerjhood 29d ago

Show HN: bb, an agentic IDE that can control itself

bb: Agentic IDE enabling orchestration of multiple coding agents with live thread control. Available as web app, CLI, and HTTP API.

HN AuthPlane 29d ago

Show HN: AuthPlane – OAuth 2.1 and PKCE authorization server for MCP

AuthPlane: OAuth 2.1 and PKCE authorization server for MCP with deterministic workflow for AI coding agents. AGPL-3.0 open source.

HN swatiahuja 29d ago

Open source second brain for live meetings hidden from screenshare

Open-source on-screen AI copilot for live meetings with real-time transcription. Supports Claude, GPT, Gemini, Ollama, and OpenAI-compatible endpoints.

HN adamrezich 29d ago

FMAG: A single-instruction GPU virtual machine and toolchain

Single-instruction GPU virtual machine and toolchain for runtime program execution without divergence concerns.

YT DeepLearningAI 29d ago

Voice for AI Agents and Applications

Title only with no content provided.

HN soheilpro 29d ago

Improving token efficiency in GitHub Copilot

GitHub Copilot token efficiency improvements for agentic sessions. Discusses harness-level optimizations to reduce token consumption across model generations.

HN skidrow 29d ago

FP8 GEMM Optimization on AMD CDNA4 Architecture

Technical optimization guide for FP8 GEMM kernels on AMD CDNA4 MI355X GPUs using Matrix Cores for machine learning computations.

HN syumei 29d ago

How Claude Code Broke My Git Worktree

Analysis of how Claude Code agent can interfere with Git Worktree environments, discussing sandbox isolation challenges for multiple agents.

HN skidrow 29d ago

Occupancy Math on the AMD MI355X: A From-First-Principles Guide

Deep technical guide deriving GPU occupancy from first principles on AMD MI355X, explaining kernel resource usage and hardware limits for performance tuning.

HN lolu1032 29d ago

Show HN: Code and reviews that only count if they survive an attack

Pantheon technique for generating multiple AI agent solutions and reviewing code survival through adversarial testing, with unclear technical details.

HN michalsustr 29d ago

Frame perfect: Syncing cursor position and app rendering

egui-cursor Rust crate syncs cursor rendering with app visuals in egui/eframe applications to eliminate perceived latency.

HN ocamoss 29d ago

How to get your agent to use Pyrefly for type checking [video]

Video showing how to configure AI agents to use Pyrefly for type checking in Python development workflows.

HN _han 29d ago

Explainer for the Cross-Origin Storage API

Cross-Origin Storage API proposal for web apps to store/retrieve files across origins, supporting AI models and WebAssembly modules with hash-based identification.

HN sohkamyung 29d ago

FairScan: An Android app to scan your documents

FairScan is an open-source Android app for scanning documents to PDF with privacy focus, minimal permissions, and no tracking.

HN cryptoSympozium 29d ago

Ask HN: Does your mind drift while waiting for AI prompts to finish?

Personal anecdote about mind drifting while waiting for AI to complete tasks. Incomplete post.

HN modinfo 29d ago

Ask HN: How much we change since LLM era?

Vague HN question about changes since LLM era with no content or discussion provided.

HN xducn1 29d ago

Show HN: OpenTalk2HTML – Convert video meeting transcripts to readable HTML

Open-source SDK for per-agent LLM cost attribution across providers (OpenAI, Anthropic, Bedrock, Gemini, Mistral) with budget enforcement and fallback routing.

HN ahmed_duski 29d ago

Show HN: Noema64 – an open-source LLM chess engine (still in beta though)

Article about fertility decline statistics. Off-topic, title only.