Ax Eduardo Sebasti\'an, Nicolas Pfitzer, Ajay Shankar, Amanda Prorok 13d ago

Prompting Robot Teams with Natural Language

Framework for prompting multi-robot teams with natural language, decomposing collaborative tasks without runtime LLM calls.

Ax Simon Idoko, Prajyot Jadhav, Arun Kumar Singh 13d ago

Flow-Opt: Scalable Centralized Multi-Robot Trajectory Optimization with Flow Matching and Differentiable Optimization

Flow-Opt uses flow matching and differentiable optimization for scalable multi-robot trajectory planning.

Ax Ji Cao, Yu Wang, Tongya Zheng, Jie Song, Qinghong Guo, Zujie Ren, Canghong Jin, Gang Chen, Mingli Song 13d ago

Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning

Trajectory representation learning encodes route choice semantics for travel time and mobility prediction tasks.

Ax Shijie Zhou, Viet Dac Lai, Hao Tan, Jihyung Kil, Wanrong Zhu, Changyou Chen, Ruiyi Zhang 13d ago

GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding

GUI-AIMA aligns multimodal attention for precise GUI grounding in computer-use agents via coordinate-free approach.

Ax Christian Lagemann, Sajeda Mokbel, Miro Gondrum, Mario R\"uttgers, Yuning Wang, Pol Su\'arez, Ludger Paehler, Deniz A. Bezgin, Aaron B. Buhendwa, Jared L. Callaham, Samuel Ahnert, Nicholas Zolman, Xiao Shao, Jean-Christophe Loiseau, Nikolaus Adams, Matthias Meinke, Wolfgang Schr\"oder, Kai Lagemann, Esther Lagemann, Ricardo Vinuesa, Steven L. Brunton 13d ago

The HydroGym Reinforcement Learning Platform for Fluid Dynamics

HydroGym is a reinforcement learning benchmark platform for fluid dynamics control and modeling.

Ax Hannah Cyberey, Yangfeng Ji, David Evans 13d ago

White-Box Sensitivity Auditing with Steering Vectors

White-Box Sensitivity Auditing uses steering vectors for interpretable LLM auditing beyond black-box testing.

Ax Olga Graf, Dhrupal Patel, Peter Gro{\ss}, Charlotte Lempp, Matthias Hein, Fabian Heinemann 13d ago

Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomalies

Anomaly detection framework for histopathology whole-slide images identifies toxicity and pathologies in preclinical screening.

Ax Xiaxian Ou, Razieh Nabi 13d ago

Coarsening Bias from Variable Discretization in Causal Functionals

Addresses statistical bias from discretizing continuous variables in causal inference functionals.

Ax Riccardo Rota, Kiril Ratmanski, Jozef Coldenhoff, Milos Cernak 13d ago

An Interpretable, Controllable Time-Varying IIR Denoiser for On-Device Assistive Hearing

TVF presents interpretable time-varying IIR filters for real-time on-device speech enhancement in hearing aids.

Ax David McAllister, Miika Aittala, Tero Karras, Janne Hellsten, Angjoo Kanazawa, Timo Aila, Samuli Laine 13d ago

Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models

Finite Difference Flow Optimization applies reinforcement learning to post-train diffusion models for improved image synthesis.

Ax Chika Maduabuchi, Jindong Wang 13d ago

Event-Driven Video Generation

Event-Driven Video Generation improves text-to-video models by selectively updating latent regions based on event interactions.

Ax Andrew Seohwan Yu, Mohsen Hariri, Kunio Nakamura, Mingrui Yang, Xiaojuan Li, Vipin Chaudhary 13d ago

Medical Image Spatial Grounding with Semantic Sampling

Medical image spatial grounding framework extends vision-language models to 3D anatomical structure localization in medical imaging.

Ax Ivor J. A. Simpson, Neill D. F. Campbell 13d ago

Structured SIR: Efficient and Expressive Importance-Weighted Inference for High-Dimensional Image Registration

Structured SIR improves probabilistic inference for image registration using flexible posterior approximations.

Ax Aditi Naiknaware, Salimeh Sekeh 13d ago

T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World

T-QPM extends vision-language models for out-of-distribution detection and domain generalization under temporal distribution shifts.

Ax Ezgi Ozyilkan, Zhiqi Chen, Oren Rippel, Jona Ball\'e, Kedar Tatwawadi 13d ago

Drop-In Perceptual Optimization for 3D Gaussian Splatting

Perceptual optimization strategies for 3D Gaussian Splatting including first large-scale human subjective study with 39k pairwise comparisons.

Ax Nahyuk Lee, Zhiang Chen, Marc Pollefeys, Sunghwan Hong 13d ago

TORA: Topological Representation Alignment for 3D Shape Assembly

TORA: topology-first representation alignment framework for 3D shape assembly using flow-matching methods with relational structure guidance.

Ax Zhuonan Yang, Jacob Xiaochen Li, Francisco Piedrahita Velez, Eric Todd, David Bau, Michael L. Littman, Stephen H. Bach, Ellie Pavlick 13d ago

Shared Lexical Task Representations Explain Behavioral Variability In LLMs

Analysis of prompt sensitivity in LLMs, showing shared lexical task representations explain behavioral variability between instruction and example-based prompting.

Ax Lingxi Zhang, Guangtao Zheng, Hanjie Chen 13d ago

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems

Study of embedding-based defense failures in LLM multi-agent systems, showing how malicious agents can manipulate group decisions and decisions.

Ax Barbora Barancikova, Daniil Shmelev, Cristopher Salvi 13d ago

Stable and Near-Reversible Diffusion ODE Solvers for Image Editing

Stable reversible ODE solvers for diffusion model inversion enabling improved text-guided image editing without accumulated inversion error.

Ax Mouhamed Amine Bouchiha, Abdelaziz Amara Korba, Yacine Ghamri-Doudane 13d ago

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

ABC-DFL: automated Byzantine-resilient decentralized federated learning framework for EV battery intelligence with privacy preservation.

Ax Madhulatha Mandarapu, Sandeep Kunkunuru 13d ago

Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations

AssetOpsBench study showing knowledge graphs significantly improve LLM agent accuracy for industrial asset operations reasoning over structured data.

Ax Tomoki Koike, Prakash Mohan, Marc T. Henry de Frahan, Elizabeth Qian, Julie Bessac 13d ago

Sparse POD Mode Selection and Manifold Dimensionality Reduction with Neural Networks

Neural network methods for sparse POD mode selection and manifold dimensionality reduction for high-dimensional data with slowly decaying singular values.

Ax Yujiao Chen 13d ago

Prospect-Theory Behavior from Bellman Optimality in MDPs with Catastrophic States

Theoretical study showing how Bellman optimality in MDPs with catastrophic states produces prospect-theory-like decision behavior without explicit loss aversion.

Ax Jessica Rodrigues, Angelo Salatino, Gard Jenset, Scott Hale 13d ago

Representing Research Attention as Contextually Structured Flows

Framework for representing research attention as contextually structured flows to better interpret societal impact of research outputs beyond raw metrics.

Ax Arthur Bouton, Tristan D. Hasseler, Michael Paton, Travis Brown, Jacob Levy, William Reid, Joshua Martin, Hari Nayar 13d ago

Learning All-Terrain Locomotion for a Planetary Rover with Actively Articulated Suspension

ERNEST: planetary rover with active gimbal suspension controlled by a single neural network trained for autonomous terrain navigation and obstacle negotiation.

Ax Huixi Technology, :, Chen Zhang, Chenyang Zhou, Guanglei Ding, Guanghui He, Haibin Gao, Jiajia Chen, Jianyong Zhang, Lianyi Yu, Ningyi Xu, Ping Xu, Qingchen Li, Yingjun Hu, Yijia Zhang, Yuxi Liu 13d ago

RhinoVLA Technical Report

RhinoVLA: Vision-Language-Action model optimized for real-time robotic manipulation on edge hardware by reducing visual and context token overhead.

Ax Jimut B. Pal, Suyash P. Awate 13d ago

Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation

VarDeepPCA: lightweight variational DNN framework for refining out-of-distribution medical image segmentation with uncertainty estimation from small training sets.

Ax Aijie Shu, Bowei Chen, Wenbin Wu, Cathy Yi-Hsuan Chen, Fengxiang He 13d ago

DeXposure-Claw: An Agentic System for DeFi Risk Supervision

DeXposure-Claw: agentic system using LLMs for DeFi risk supervision, routing decisions through structured evidence for regulator-aligned decision-making.

Ax Shivam Ratnakar, Kartikeya Vats 13d ago

The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs

Mechanistic study of safety alignment in LLMs using Contrastive Logit Steering to isolate and understand the 'refusal direction' as a linear feature.

Ax Xinyu Lian, Walid Krichene, Beichen Huang, Masahiro Tanaka, Olatunji Ruwase, Li Zhang, Minjia Zhang 13d ago

Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models

Analysis of hidden inference costs in quantized reasoning LLMs, showing low-bit models generate longer chains of thought despite correct answers.

Ax Nicholas Pulsone, Gregory Goren, Roee Shraga 13d ago

Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matching

Study on entity matching in data integration pipelines using domain-aware distribution alignment and low-resource learning techniques.

Ax Louis Bagot (SyCoSMA), Mathieu Lefort (LIRIS, SyCoSMA, IRISA, MALT, UR), La\"etitia Matignon (SyCoSMA) 13d ago

Exploration and Online Transfer with Behavioral Foundation Models

Research on behavioral foundation models for zero-shot transfer in RL, enabling agents to generate optimal policies for any reward function without task-specific learning.

Ax Beryl Gnanaraj, Jaya Sreevalsan-Nair, Saqib Alam Ansari, Maanasa Rajaraman 13d ago

Consensus Clustering of Free-Viewing Gaze Data: New Insights into Human-Information Interaction

arXiv study on consensus clustering of eye-tracking gaze data to analyze human-information interaction patterns.

HN brandonb 13d ago

LLM-style scaling laws hold for sensor data

Research showing that LLM-style scaling laws (loss vs. model/dataset size) apply to sensor data, with implications for AI economics and emergent capabilities.

HN jonbaer 13d ago

Three HPC Gurus Ask: Do We Still Need GPUs?

Discussion of whether modern CPUs with vector engines and HBM can replace GPUs for HPC and AI workloads.

HN snappedai 13d ago

Local video clipping infrastructure for creators and small teams

Local video processing system that transcribes, clips, edits, and generates captions and thumbnails from raw footage without cloud dependencies.

HN hyperb1iss 13d ago

Show HN: Sibyl – self-hosted cross-agent memory for AI coding agents

Sibyl is a self-hosted, scalable agent memory system built on SurrealDB enabling parallel AI coding agents to share context and coordinate work.

HN erikschoster 13d ago

Niche LLM Spam on Bandcamp

Headline only: LLM spam detected on Bandcamp music platform.

HN jnord 13d ago

Claude Code users complain their chat records are being mysteriously wiped out

Claude Code users report silent deletion of conversation transcripts older than 30 days due to a non-obvious default setting.

HN arman-w-jalili 13d ago

Show HN: Coding agent that compiles intent into deterministic DAG before running

Rigorix compiles natural language development tasks into deterministic DAGs for repeatable, auditable AI-assisted software engineering with policy constraints.

HN nickpismenkov 13d ago

Show HN: Agentic OS – the operating system for AI agents

Agentic OS: proactive AI assistant for automating tasks, scheduling, and file management. Limited details provided.

HN shikhar 13d ago

Serving Local AI on My Jetson Through Durable Streams

Tutorial on self-hosting LLMs on NVIDIA Jetson Orin Nano for local inference without third-party APIs.

HN isfttr 13d ago

Anthropic launches Claude Science: an AI workbench for scientists (2026)

Anthropic launches Claude Science: specialized LLM workbench for scientific research. Announcement stub.

HN steilpass 13d ago

Guardians of the Agents Formal verification of AI workflows. (Dec 2025)

Guardians of the Agents: formal verification methods for AI workflows. Limited content.

HN sleepynoodle 13d ago

Llmaker – spin up a working LLM app from a single prompt, right in your terminal

llmaker: open-source platform for running complete LLM stack locally with models, vector DB, embeddings, retrieval, and agents. Single-command deployment.

HN s314 13d ago

Ovid: A pi extension that makes it record proof its features actually work

Ovid is a tool that verifies AI coding agent features work by recording proof videos; integrates with pi agent and supports any-language projects.

HN gittrend 13d ago

OpenMontage: an open-source agent that edits real footage into video

OpenMontage is an open-source AI agent system that automates video production tasks including research, scripting, asset generation, editing, and composition from plain language descriptions.

HN c7ma23s 13d ago

Show HN: Yourself, in Every Light

Alma: local-first MCP server for AI agents to maintain persistent user context (name, preferences, values) across vendors without vendor lock-in.

HN OsamaJaber 13d ago

RunInfra: Optimize any open model down to the kernel, deploy in 5 min

RunInfra: automated model optimization and deployment. Benchmarks models, kernels, GPUs and generates deployment kits in 5 minutes.

HN himata4113 13d ago

Claude Sonnet 5: strong agentic performance at a higher cost per task

Claude Sonnet 5 benchmarking: achieves 53 on Intelligence Index with higher cost-per-task than Opus 4.8.