Search: “models”

DanceCrafter: Fine-Grained Text-Driven Controllable Dance Generation via Choreographic Syntax

arXiv:2604.18648v1 Announce Type: cross Abstract: Text-driven controllable dance generation remains under-explored, primarily due to the severe scarcity of high-quality datasets and the inherent diffi

Agents

Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection

DGX agent

arXiv:2604.19005v1 Announce Type: new Abstract: Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on expli

agentsarxiv-cs-cl

22 Apr 2026

Tutorials

Disentangling Damage from Operational Variability: A Label-Free Self-Supervised Representation Learning Framework for Output-Only Structural Damage Identification

arXiv:2604.19658v1 Announce Type: new Abstract: Damage identification is a core task in structural health monitoring. In practice, however, its reliability is often compromised by confounding non-dama

tutorialsarxiv-cs-lg

Enabling Vibration-Based Gesture Recognition on Everyday Furniture via Energy-Efficient FPGA Implementation of 1D Convolutional Networks

arXiv:2510.23156v2 Announce Type: replace-cross Abstract: The growing demand for smart home interfaces has increased interest in non-intrusive sensing methods like vibration-based gesture recognition.

applicationsarxiv-cs-ai

Enhancing Unsupervised Keyword Extraction in Academic Papers through Integrating Highlights with Abstract

arXiv:2604.19505v1 Announce Type: cross Abstract: Automatic keyword extraction from academic papers is a key area of interest in natural language processing and information retrieval. Although previou

researcharxiv-cs-cl

Epistemic orientation in parliamentary discourse is associated with deliberative democracy

arXiv:2604.19699v1 Announce Type: new Abstract: The pursuit of truth is central to democratic deliberation and governance, yet political discourse reflects varying epistemic orientations, ranging from

researcharxiv-cs-cl

Evaluating LLM-Driven Summarisation of Parliamentary Debates with Computational Argumentation

arXiv:2604.19331v1 Announce Type: new Abstract: Understanding how policy is debated and justified in parliament is a fundamental aspect of the democratic process. However, the volume and complexity of

safetyarxiv-cs-cl

Explicit Trait Inference for Multi-Agent Coordination

arXiv:2604.19278v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) show promise on complex tasks but remain prone to coordination failures such as goal drift, error cascades, and misa

agentsarxiv-cs-ai

Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents

arXiv:2604.19034v1 Announce Type: new Abstract: Constructing structured spatial memory is essential for enabling long-horizon reasoning in complex embodied navigation tasks. Current memory constructio

agentsarxiv-cs-cv

FASTER: Value-Guided Sampling for Fast RL

arXiv:2604.19730v1 Announce Type: cross Abstract: Some of the most performant reinforcement learning algorithms today can be prohibitively expensive as they use test-time scaling methods such as sampl

From Top-1 to Top-K: A Reproducibility Study and Benchmarking of Counterfactual Explanations for Recommender Systems

arXiv:2604.19663v1 Announce Type: cross Abstract: Counterfactual explanations (CEs) provide an intuitive way to understand recommender systems by identifying minimal modifications to user-item interac

applicationsarxiv-cs-lg

Generalization at the Edge of Stability

arXiv:2604.19740v1 Announce Type: cross Abstract: Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit osci

Local Ai

Generative Drifting for Conditional Medical Image Generation

arXiv:2604.19736v1 Announce Type: new Abstract: Conditional medical image generation plays an important role in many clinically relevant imaging tasks. However, existing methods still face a fundament

local-aiarxiv-cs-cv

GOLD-BEV: GrOund and aeriaL Data for Dense Semantic BEV Mapping of Dynamic Scenes

arXiv:2604.19411v1 Announce Type: cross Abstract: Understanding road scenes in a geometrically consistent, scene-centric representation is crucial for planning and mapping. We present GOLD-BEV, a fram

Google Cloud and Wiz debut new AI security agents at Next '26, including Threat Hunting and Detection Engineering agents, to combat automated zero-day exploits (Frederic Lardinois/The New Stack)

Frederic Lardinois / The New Stack: Google Cloud and Wiz debut new AI security agents at Next '26, including Threat Hunting and Detection Engineering agents, to combat automated zero-day exploits — Th

Groundcover adds agentic AI tracing to observability platform, backs Google Vertex AI

Application observability startup groundcover Ltd. today announced a major expansion of its AI Observability capability, adding native support for agentic AI systems fully compatible with Google Verte

agentssiliconangle

I kinda think it would be interesting to have a structure where founders take 2 and 20 2% management fee on capital raised for running the c…

I kinda think it would be interesting to have a structure where founders take 2 and 20 2% management fee on capital raised for running the company 20% of any exit Single magic share with lots of votin

industryemad-mostaque--x

Idle is the New Sleep: Configuration-Aware Alternative to Powering Off FPGA-Based DL Accelerators During Inactivity

arXiv:2407.12027v2 Announce Type: replace-cross Abstract: In the rapidly evolving Internet of Things (IoT) domain, we concentrate on enhancing energy efficiency in Deep Learning accelerators on FPGA-b

Implicit Neural Field-Based Process Planning for Multi-Axis Manufacturing: Direct Control over Collision Avoidance and Toolpath Geometry

arXiv:2511.17578v2 Announce Type: replace Abstract: Existing curved-layer-based process planning methods for multi-axis manufacturing address collisions only indirectly and generate toolpaths in a pos

applicationsarxiv-cs-ro

Integrating Anomaly Detection into Agentic AI for Proactive Risk Management in Human Activity

arXiv:2604.19538v1 Announce Type: new Abstract: Agentic AI, with goal-directed, proactive, and autonomous decision-making capabilities, offers a compelling opportunity to address movement-related risk

>LangChain gives you testing tools. It never tells you what to test, in what order, or when you're done. This is changing soon Launching May…

LangChain is introducing new testing tools and capabilities that will help developers with test guidance, organization, and completion criteria—moving beyond just providing testing infrastructure to a

agentsharrison-chase--x

LASER: Learning Active Sensing for Continuum Field Reconstruction

arXiv:2604.19355v1 Announce Type: cross Abstract: High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under spa

Local Ai

Localization-Guided Foreground Augmentation in Autonomous Driving

arXiv:2604.18940v1 Announce Type: new Abstract: Autonomous driving systems often degrade under adverse visibility conditions-such as rain, nighttime, or snow-where online scene geometry (e.g., lane di

local-aiarxiv-cs-cv

Mind2Drive: Predicting Driver Intentions from EEG in Real-world On-Road Driving

arXiv:2604.19368v1 Announce Type: new Abstract: Predicting driver intention from neurophysiological signals offers a promising pathway for enhancing proactive safety in advanced driver assistance syst

safetyarxiv-cs-cv

Multi-Gait Learning for Humanoid Robots Using Reinforcement Learning with Selective Adversarial Motion Prior

arXiv:2604.19102v1 Announce Type: cross Abstract: Learning diverse locomotion skills for humanoid robots in a unified reinforcement learning framework remains challenging due to the conflicting requir

Local Ai

Multi-Level Temporal Graph Networks with Local-Global Fusion for Industrial Fault Diagnosis

arXiv:2604.18765v1 Announce Type: cross Abstract: Fault detection and diagnosis are critical for the optimal and safe operation of industrial processes. The correlations among sensors often display no

local-aiarxiv-cs-ai

Multi-Step Gaussian Process Propagation for Adaptive Path Planning

arXiv:2604.19148v1 Announce Type: new Abstract: Efficient and robust path planning hinges on combining all accessible information sources. In particular, the task of path planning for robotic environm

agentsarxiv-cs-ro

New Technical Report from @EkagraRanjan: Contrary to what you might expect, MoE-based LLMs make speculative decoding even more effective. Re…

New Technical Report from @EkagraRanjan: Contrary to what you might expect, MoE-based LLMs make speculative decoding even more effective. Read more on our blog: Ever wondered how Speculative Decoding

applicationscohere--x

Next '26 Hands-On: 10 Codelabs to Build Featured Tech

Significant contributors to this article include Megan O'Keefe, Senior Staff Developer Advocate, and Karl Weinmeister, Director of Developer Relations. Whether you are joining us in person in Las Vega

agentsgoogle-cloud-ai

Online Learning of Whittle Indices for Restless Bandits with Non-Stationary Transition Kernels

arXiv:2506.18186v3 Announce Type: replace Abstract: The restless multi-armed bandit (RMAB) framework is a popular approach to solving resource allocation problems in networked systems. In this paper,

safetyarxiv-cs-lg

Our newsroom AI policy

Ars Technica's newsroom AI policy forbids unlabeled AI material in reported stories and requires human confirmation of every quotation's accuracy. The publication does not permit the publication of AI

safetyars-technica

PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving

arXiv:2604.19379v1 Announce Type: new Abstract: This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve general

agentsarxiv-cs-cv

persistence always pays off, even for ml interns (btw, I haven't done anything for the past 30 mins, just observing the intern making mistak…

This post from Hugging Face CEO Clem Delangue discusses the value of persistence in machine learning work, using an anecdote about observing an intern working through problems. The tweet emphasizes th

industryclem-delangue--x

Phase Transitions in the Fluctuations of Functionals of Random Neural Networks

arXiv:2604.19738v1 Announce Type: cross Abstract: We establish central and non-central limit theorems for sequences of functionals of the Gaussian output of an infinitely-wide random neural network on

researcharxiv-cs-lg

Planning in entropy-regularized Markov decision processes and games

arXiv:2604.19695v1 Announce Type: new Abstract: We propose SmoothCruiser, a new planning algorithm for estimating the value function in entropy-regularized Markov decision processes and two-player gam

researcharxiv-cs-lg

Quantum spatial best-arm identification via quantum walks

arXiv:2509.05890v3 Announce Type: replace-cross Abstract: Quantum reinforcement learning has emerged as a framework combining quantum computation with sequential decision-making, and applications to t

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery

arXiv:2604.19049v1 Announce Type: cross Abstract: LLM-assisted defect discovery has a precision crisis: plausible-but-wrong reports overwhelm maintainers and degrade credibility for real findings. We

agentsarxiv-cs-ai

Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports

arXiv:2604.19060v1 Announce Type: new Abstract: Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improv

RF-HiT: Rectified Flow Hierarchical Transformer for General Medical Image Segmentation

arXiv:2604.19570v1 Announce Type: new Abstract: Accurate medical image segmentation requires both long-range contextual reasoning and precise boundary delineation, a task where existing transformer- a

researcharxiv-cs-cv

Robust Continual Unlearning against Knowledge Erosion and Forgetting Reversal

arXiv:2604.19108v1 Announce Type: cross Abstract: As a means to balance the growth of the AI industry with the need for privacy protection, machine unlearning plays a crucial role in realizing the ``r

researcharxiv-cs-cv

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving

arXiv:2604.19157v1 Announce Type: new Abstract: KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and hi

applicationsarxiv-cs-lg

Scripts Through Time: A Survey of the Evolving Role of Transliteration in NLP

arXiv:2604.18722v1 Announce Type: new Abstract: Cross-lingual transfer in NLP is often hindered by the ``script barrier'' where differences in writing systems inhibit transfer learning between languag

researcharxiv-cs-cl

Sean Plankey, President Trump's pick to lead CISA, withdraws from consideration after resistance from Sen. Rick Scott stalled his nomination for over a year (Politico)

Politico: Sean Plankey, President Trump's pick to lead CISA, withdraws from consideration after resistance from Sen. Rick Scott stalled his nomination for over a year — Spokespeople for the White Hous

Sony AI says its autonomous ping pong robot is the first robot to attain expert-level performance in a physical sport after beating some top-level human players (Will Dunham/Reuters)

Will Dunham / Reuters: Sony AI says its autonomous ping pong robot is the first robot to attain expert-level performance in a physical sport after beating some top-level human players — An autonomous

agentstechmeme

Hardware

Source: Mira Murati's TML signed a deal with Google Cloud, valued in single-digit billions, to access Google's latest AI systems built on Nvidia's GB300 chips (Rebecca Bellan/TechCrunch)

Rebecca Bellan / TechCrunch: Source: Mira Murati's TML signed a deal with Google Cloud, valued in single-digit billions, to access Google's latest AI systems built on Nvidia's GB300 chips — Former Ope

hardwaretechmeme

Sources detail how Elon Musk has de-emphasized SpaceX's original aim of reaching Mars as it prepares to go public, focusing instead on AI and other moonshots (Ryan Mac/New York Times)

Ryan Mac / New York Times: Sources detail how Elon Musk has de-emphasized SpaceX's original aim of reaching Mars as it prepares to go public, focusing instead on AI and other moonshots — For years, Sp

Sources: SpaceX isn't acquiring Cursor immediately because the deal could delay its IPO; Cursor is no longer proceeding with its reported $2B funding round (Bloomberg)

Bloomberg: Sources: SpaceX isn't acquiring Cursor immediately because the deal could delay its IPO; Cursor is no longer proceeding with its reported 2B funding round — SpaceX said it has an agreement

Speeding up agentic workflows with WebSockets in the Responses API

This OpenAI article describes how to use WebSockets with the Responses API to improve performance and reduce latency in agentic AI workflows. WebSockets enable real-time, bidirectional communication b

agentsopenai