Search: “applications”

Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach

arXiv:2605.12974v1 Announce Type: new Abstract: In this work, we study how to ensure probabilistic safety for nonlinear systems under distributional ambiguity. Our approach builds on a backup-based sa

safetyarxiv-cs-ro

Research

Does language matter for spoken word classification? A multilingual generative meta-learning approach

DGX agent

arXiv:2605.13084v1 Announce Type: cross Abstract: Meta-learning has been shown to have better performance than supervised learning for few-shot monolingual spoken word classification. However, the met

researcharxiv-cs-ai

14 May 2026

DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning

arXiv:2605.13418v1 Announce Type: new Abstract: Differentially private optimization suffers from a fundamental geometric mismatch: deep networks have highly anisotropic loss landscapes, yet DP-SGD inj

Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation

arXiv:2605.13315v1 Announce Type: cross Abstract: Biological neural networks (BNNs) have been established as a powerful and adaptive substrate that offer the potential for incredibly energy and data e

EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents

arXiv:2605.13841v1 Announce Type: cross Abstract: Voice agents, artificial intelligence systems that conduct spoken conversations to complete tasks, are increasingly deployed across enterprise applica

Exact Sequence Interpolation with Transformers

arXiv:2502.02270v3 Announce Type: replace Abstract: We prove that transformers can exactly interpolate datasets of finite input sequences in R^d, dgeq 2, with corresponding output sequences of smaller

Few-Shot Physics-Informed Neural Network for Shape Reconstruction of Concentric-Tube Robots

arXiv:2605.12790v1 Announce Type: new Abstract: Modeling concentric tube robots (CTRs) involves complex nonlinear continuum mechanics, and despite recent progress, physics-based models often lack an a

Flow Matching for Offline Reinforcement Learning with Discrete Actions

arXiv:2602.06138v2 Announce Type: replace Abstract: Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applica

safetyarxiv-cs-lg

Hardware

Geometric Autoencoder Priors for Bayesian Inversion: Learn First Observe Later

arXiv:2509.19929v4 Announce Type: replace-cross Abstract: Uncertainty Quantification (UQ) is paramount for inference in engineering. A common inference task is to recover full-field information of phy

hardwarearxiv-cs-lg

GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans

model-releasesarxiv-cs-cv

arXiv:2505.05376v3 Announce Type: replace Abstract: We propose a novel method that reconstructs hair strands directly from colorless 3D scans by leveraging multi-modal hair orientation extraction. Hai

Tools

Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality

Granite Embedding Multilingual R2 is an open-source multilingual embedding model released by IBM under the Apache 2.0 license, featuring a 32K context window and sub-100M parameters. The model is opti

toolshugging-face

Hierarchical Transformer Preconditioning for Interactive Physics Simulation

arXiv:2605.13343v1 Announce Type: cross Abstract: Neural preconditioners for real-time physics simulation offer promising data-driven priors, but they often fail to capture long-range couplings effici

Identifying the nonlinear string dynamics with port-Hamiltonian neural networks

arXiv:2605.12785v1 Announce Type: new Abstract: Hybrid machine learning combines physical knowledge with data-driven models to enhance interpretability and performance. In this context, Port-Hamiltoni

IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages

arXiv:2605.13292v1 Announce Type: cross Abstract: Most existing medical dialogue systems operate in a single-turn question--answering paradigm or rely on template-based datasets, limiting conversation

LangChain Labs is live

LangChain Labs has launched as a new initiative from the LangChain team. The announcement was made by Harrison Chase, the creator and lead developer of LangChain, on X (formerly Twitter). LangChain La

agentsharrison-chase--x

Local Ai

Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs

arXiv:2605.12714v1 Announce Type: new Abstract: Hidden states change substantially across the layers of modern language models, but most layer-wise analyses focus on one aspect of that change. We prop

local-aiarxiv-cs-lg

Learning to Approximate Uniform Facility Location via Graph Neural Networks

arXiv:2602.13155v2 Announce Type: replace Abstract: Neural networks, particularly message-passing neural networks (MPNNs), are increasingly used as heuristics for hard combinatorial optimization probl

Lifelong Learning in Vision-Language Models: Enhanced EWC with Cross-Modal Knowledge Retention

arXiv:2605.12789v1 Announce Type: new Abstract: Large language-vision models (LVLMs) such as CLIP, Flamingo, and BLIP have revolutionized AI by enabling understanding across textual and visual modalit

Limitations of Quantum Advantage in Unsupervised Machine Learning

arXiv:2511.10709v2 Announce Type: replace-cross Abstract: Machine learning models are used for pattern recognition analysis of big data, without direct human intervention. The task of unsupervised lea

Local Ai

LLM Flow Processes for Text-Conditioned Regression

arXiv:2601.06147v2 Announce Type: replace Abstract: Recent work has demonstrated surprisingly good performance of pre-trained LLMs on regression tasks (for example, time-series prediction), with the a

local-aiarxiv-cs-lg

Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters

arXiv:2512.16767v2 Announce Type: replace Abstract: Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-c

researcharxiv-cs-cv

MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence

arXiv:2605.12703v1 Announce Type: cross Abstract: We introduce MMCL-Bench, a benchmark for multimodal context learning: learning task-local rules, procedures, and empirical patterns from visual or mix

MoCCA: A Movable Circle Probability of Collision Approximation

arXiv:2605.13125v1 Announce Type: new Abstract: In automated driving, crash mitigation is crucial to ensure passenger safety. Accurate avoidance requires precise knowledge of the object's position and

safetyarxiv-cs-ro

Multi-Depth Uniform Coverage Path Planning for Unmanned Surface Vehicle Surveying

arXiv:2605.13123v1 Announce Type: new Abstract: This paper introduces a novel automatic coverage path planning algorithm for bathymetry surveying with unmanned surface vehicles. The detection range of

agentsarxiv-cs-ro

Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using Large Language Model Judges with Closed-Loop Reinforcement Learning Feedback

arXiv:2605.05739v2 Announce Type: replace-cross Abstract: Forecast evaluation in finance has relied on aggregate accuracy metrics and predictive-accuracy tests built on point-forecast errors. These in

agentsarxiv-cs-ai

Profit Maximization in Bilateral Trade against a Smooth Adversary

arXiv:2605.12664v1 Announce Type: cross Abstract: Bilateral trade models the task of intermediating between two strategic agents, a seller and a buyer, who wish to trade a good. We study this problem

R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

arXiv:2605.13838v1 Announce Type: new Abstract: Video-guided 3D animation holds immense potential for content creation, offering intuitive and precise control over dynamic assets. However, practical d

safetyarxiv-cs-cv

RAG-GNN: Integrating Retrieved Knowledge with Graph Neural Networks for Precision Medicine

arXiv:2602.00586v2 Announce Type: replace-cross Abstract: Network topology excels at structural predictions but fails to capture functional semantics encoded in biomedical literature. We present RAG-G

safetyarxiv-cs-ai

Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes

arXiv:2605.13591v1 Announce Type: new Abstract: Reliable autonomous driving relies on large-scale, well-labeled data and robust models. However, manual data collection is resource-intensive, and tradi

safetyarxiv-cs-cv

Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspective

arXiv:2605.13597v1 Announce Type: new Abstract: Graph neural networks (GNNs) have emerged as a fundamental tool for learning from graph-structured data, achieving strong performance across a wide rang

Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale

arXiv:2605.13684v1 Announce Type: new Abstract: We study the optimal scale at which real-valued function classes exhibit uniform convergence and learnability. Our main result establishes a scale-sensi

SCU-Hand with Integrated Single-Sheet Valve: A Funnel-Shaped Robotic Hand for Milligram-Scale Powder Handling

arXiv:2512.07091v2 Announce Type: replace Abstract: Laboratory Automation (LA) has the potential to accelerate solid-state materials discovery by enabling continuous robotic operation without human in

Stable Attention Response for Reliable Precipitation Nowcasting

arXiv:2605.13181v1 Announce Type: cross Abstract: Precipitation nowcasting remains challenging due to the highly localized, rapidly evolving, and heterogeneous nature of atmospheric dynamics. Although

researcharxiv-cs-ai

StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos

arXiv:2512.01707v3 Announce Type: replace-cross Abstract: Streaming video understanding requires models not only to process temporally incoming frames, but also to anticipate user intention for realis

Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning

arXiv:2605.13207v1 Announce Type: new Abstract: Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing a

safetyarxiv-cs-lg

The critical slowing down in diffusion models

arXiv:2605.12597v1 Announce Type: cross Abstract: Computational sampling has been central to the sciences since the mid-20th century. While machine-learning-based approaches have recently enabled majo

Tutorials

The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks

arXiv:2605.13690v1 Announce Type: cross Abstract: Hypergraphs provide a natural framework to model higher-order interactions in scientific, social, and biological systems. Hypergraph neural networks (

tutorialsarxiv-cs-ai

Unweighted ranking for value-based decision making with uncertainty

arXiv:2605.13601v1 Announce Type: new Abstract: As intelligent systems are increasingly implemented in our society to make autonomous decisions, their commitment to human values raises serious concern

safetyarxiv-cs-ai

VIP-COP: Context Optimization for Tabular Foundation Models

arXiv:2605.12904v1 Announce Type: new Abstract: Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabul

Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?

arXiv:2605.12684v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of thes

Yesterday we gave an in-person NYC workshop on automating your financial document ingestion pipelines with AI. If you're an investment bank,…

Yesterday we gave an in-person NYC workshop on automating your financial document ingestion pipelines with AI. If you're an investment bank, accounting team, finance AI startup, fintech company, and y

agentsjerry-liu--x

3DGS^3: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering

model-releasesarxiv-cs-cv

arXiv:2605.11489v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) enables high-quality real-time 3D rendering but faces challenges in efficiently scaling to ultra-dense scenes and high-re

Local Ai

A Fast and Energy-Efficient Latch-Based Memristive Analog Content-Addressable Memory

arXiv:2605.11847v1 Announce Type: cross Abstract: Analog content-addressable memories (aCAMs) based on memristors provide a promising pathway toward energy-efficient large-scale associative computing

local-aiarxiv-cs-lg

A Proprioceptive-Only Benchmark for Quadruped State Estimation: ATE, RPE, and Runtime Trade-offs Between Filters and Smoothers

arXiv:2605.11674v1 Announce Type: new Abstract: We compare three state-of-the-art proprioceptive state estimators for quadruped robots: MUSE [1], the Invariant Extended Kalman Filter (IEKF) [2], and t

A Study on Hidden Layer Distillation for Large Language Model Pre-Training

model-releasesarxiv-cs-cl

arXiv:2605.11513v1 Announce Type: new Abstract: Knowledge Distillation (KD) is a critical tool for training Large Language Models (LLMs), yet the majority of research focuses on approaches that rely s

Industry

/brainpower_podcast/season_2/episode_3/emad_mostaque is live featuring @EMostaque (Founder of @ii_posts). Hosted by @DJohnstonEC (@MorpheusA…

This episode features Emad Mostaque, founder of Stability AI, in a live podcast discussion hosted by David Johnston. The conversation likely covers topics related to AI development, Stability AI's pro

industryemad-mostaque--x

Hardware

Cerebras — Faster Tokens Please

Cerebras, a company specializing in AI accelerators and wafer-scale computing systems, is discussed in terms of its approaches to improving token generation speed in large language models, which is cr

hardwaresemianalysis

Coordinated Diffusion: Generating Multi-Agent Behavior Without Multi-Agent Demonstrations

arXiv:2605.11485v1 Announce Type: new Abstract: Imitation learning powered by generative models has proven effective for modeling complex single-agent behaviors. However, teaching multi-agent systems,

safetyarxiv-cs-ro