Search: “models”

Why is ComfyUI no longer working on RunPod? how can i solve this?

local-air-stablediffusion

Users encountering ComfyUI failures on RunPod often face connection initialization issues, including 'Bad Gateway' errors that can be resolved by waiting 2–3 minutes for the HTTP service to fully star

23 Apr 2026

Agents

A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends

DGX agent

arXiv:2507.09861v2 Announce Type: replace-cross Abstract: Visually Rich Document Understanding (VRDU) has become a pivotal area of research, driven by the need to automatically interpret documents tha

agentsarxiv-cs-ai

22 Apr 2026

Accelerating trajectory optimization with Sobolev-trained diffusion policies

arXiv:2604.19011v1 Announce Type: new Abstract: Trajectory Optimization (TO) solvers exploit known system dynamics to compute locally optimal trajectories through iterative improvements. A downside is

local-aiarxiv-cs-lg

Hardware

AdaGScale: Viewpoint-Adaptive Gaussian Scaling in 3D Gaussian Splatting to Reduce Gaussian-Tile Pairs

arXiv:2604.18980v1 Announce Type: new Abstract: Reducing the number of Gaussian-tile pairs is one of the most promising approaches to improve 3D Gaussian Splatting (3D-GS) rendering speed on GPUs. How

hardwarearxiv-cs-cv

Hardware

Advancing Emerging Optimizers for Accelerated LLM Training with NVIDIA Megatron

This blog post discusses higher-order optimization algorithms such as Shampoo that have been applied in neural network training for at least a decade. The article explores how these emerging optimizer

hardwarenvidia-developer

Tutorials

AI App Development: Guide To Building AI-Powered Apps

This guide covers the fundamentals and best practices for developing AI-powered applications, likely including key stages from ideation through deployment, technology stack considerations, and integra

tutorialsdatabricks

An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA

arXiv:2604.19685v1 Announce Type: new Abstract: Answering open-ended questions remains challenging for AI systems because it requires synthesis, judgment, and exploration beyond factual retrieval, and

researcharxiv-cs-cl

Anker announces Thus, a compute-in-memory chip it says will bring on-device AI to its products and accessories, starting with its upcoming Soundcore earbuds (John Higgins/The Verge)

John Higgins / The Verge: Anker announces Thus, a compute-in-memory chip it says will bring on-device AI to its products and accessories, starting with its upcoming Soundcore earbuds — The Thus chip

local-aitechmeme

Anthropic’s own internal security blows.

Anthropic’s own internal security blows. Anthropic said Mythos was too dangerous to release. Then four random guys in a Discord gained access on day one by guessing the URL... This is pretty insane: →

safetygary-marcus--x

Tools

Apparently the bug was rolling out the new pricing grid worldwide when it should only have been seen by the 2% of people in the A/B test htt…

Apparently the bug was rolling out the new pricing grid worldwide when it should only have been seen by the 2% of people in the A/B test https://x.com/TheAmolAvasare/status/2046783926920978681 Getting

toolssimon-willison--x

Autogenesis: A Self-Evolving Agent Protocol

arXiv:2604.15034v2 Announce Type: replace Abstract: Recent advances in LLM based agent systems have shown promise in tackling complex, long horizon tasks. However, existing agent protocols (e.g., A2A

agentsarxiv-cs-ai

Autonomous Skeletal Landmark Localization towards Agentic C-Arm Control

arXiv:2604.18740v1 Announce Type: new Abstract: Purpose: Automated C-arm positioning ensures timely treatment in patients requiring emergent interventions. When a conventional Deep Learning (DL) appro

local-aiarxiv-cs-cv

BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search

arXiv:2601.11037v2 Announce Type: replace Abstract: RL-based agentic search enables LLMs to solve complex questions via dynamic planning and external search. While this approach significantly enhances

Beyond Bellman: High-Order Generator Regression for Continuous-Time Policy Evaluation

arXiv:2604.18972v1 Announce Type: cross Abstract: We study finite-horizon continuous-time policy evaluation from discrete closed-loop trajectories under time-inhomogeneous dynamics. The target value s

safetyarxiv-cs-lg

CoCo-SAM3: Harnessing Concept Conflict in Open-Vocabulary Semantic Segmentation

arXiv:2604.19648v1 Announce Type: cross Abstract: SAM3 advances open-vocabulary semantic segmentation by introducing a prompt-driven mask generation paradigm. However, in multi-class open-vocabulary s

Contrast Security integrates ADR with Google Security Operations for runtime app visibility in the SOC

Application security startup Contrast Security Inc. today announced a new integration that pipes runtime application telemetry from its Application Detection and Response platform directly into Google

applicationssiliconangle

Curvature-Aware PCA with Geodesic Tangent Space Aggregation for Semi-Supervised Learning

arXiv:2604.18816v1 Announce Type: cross Abstract: Principal Component Analysis (PCA) is a fundamental tool for representation learning, but its global linear formulation fails to capture the structure

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

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

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

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

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

Industry

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

industrytechmeme

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

Industry

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

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

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