All entries

A local-first harness for multi-agent workflows

Hey all, I’ve been working on this in my spare time and finally feel ready to share it outside my own circles. Arbiter is a single binary for running agents locally. I originally built it because I wa

local-air-ollama

A Multi-Dimensional Evaluation of Explainability in Media Bias Detection

DGX agent

arXiv:2607.19954v1 Announce Type: new Abstract: Detecting media bias automatically is difficult because biased framing is often subtle, yet in domains such as news analysis, accurate predictions alone

safetyarxiv-cs-cl

23 Jul 2026

A Multiclass Quantum Aligned Centroid Kernel

model-releasesarxiv-cs-lg

arXiv:2607.19782v1 Announce Type: cross Abstract: Kernel methods are powerful tools in machine learning but commonly used full-Gram kernels face three key limitations: (1) quadratic scaling with train

A Novel Hybrid Deep Learning Technique for Speech Emotion Detection using Feature Engineering

arXiv:2507.07046v3 Announce Type: replace-cross Abstract: Nowadays, speech emotion recognition (SER) plays a vital role in the field of human-computer interaction (HCI) and the evolution of artificial

A Splitting Architecture for Exact Reduced Coulomb Friction

arXiv:2607.19599v1 Announce Type: cross Abstract: Existing approaches to frictional contact dynamics typically either modify the Coulomb law to improve numerical robustness or solve the exact law in a

researcharxiv-cs-ro

A Structure-Adaptive Random Feature Method for High-Dimensional Elliptic PDEs

arXiv:2607.19786v1 Announce Type: cross Abstract: Random-feature methods reduce high-dimensional elliptic PDE collocation to linear coefficient problems, but full-dimensional trial spaces overlook low

A Systematic Benchmark of Intensity Normalisation Methods for 3D Knee MRI Segmentation and Cross-Domain Generalisability

arXiv:2607.20028v1 Announce Type: cross Abstract: Robust out-of-the-box performance is essential for the clinical deployment of deep learning models in medical imaging. An important but underexplored

A Systematic Evaluation of Traditional Privacy Policy Analysis Tools Against LLMs

model-releasesarxiv-cs-cl

arXiv:2607.17075v2 Announce Type: replace-cross Abstract: The advent of LLMs has significantly changed the research on privacy policy and data compliance analysis by enabling tasks that previously req

A Unified Tokenization Framework for Pain Recognition using Heterogeneous 3D Modalities

model-releasesarxiv-cs-cv

arXiv:2607.19716v1 Announce Type: new Abstract: Pain is a complex and pervasive phenomenon affecting a large percentage of the population, and accurate assessment is essential for effective clinical m

A Unified Variational Framework for Deep Weakly Supervised Image Segmentation

arXiv:2607.19669v1 Announce Type: new Abstract: We propose a unified variational framework for image segmentation under sparse pixel-level supervision. Our method is based on a simplex-constrained Pot

researcharxiv-cs-cv

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

arXiv:2607.19191v1 Announce Type: new Abstract: We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data i

local-aiarxiv-cs-cv

Abstraction Induces the Brain Alignment of Language and Speech Models

arXiv:2602.04081v2 Announce Type: replace Abstract: Research has repeatedly demonstrated that intermediate hidden states extracted from large language models and speech audio models predict measured b

safetyarxiv-cs-cl

Absurd claim: the distilled model outperforms the originals

As an AI community of LLM experts, are we really going to stay silent while US officials make absurd claims to push anti-consumer laws? Not only does the release timeline between Fable and K3 make hig

local-air-localllama

Active Inference as a Convex Markov Decision Process

arXiv:2607.20152v1 Announce Type: cross Abstract: Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within

local-aiarxiv-cs-ai

AdaHome: An Adaptive Smart Home Assistant using Local Small Language Models

arXiv:2607.18034v2 Announce Type: replace Abstract: Smart home assistants interpret a wide range of user commands, from explicit device control to underspecified and preference dependent requests. Whi

local-aiarxiv-cs-ai

Adaptive Bayesian Online Learning via Expert Aggregation

arXiv:2607.20239v1 Announce Type: cross Abstract: Bayesian online learning promises uncertainty-aware prediction on data streams, but its performance hinges on inferential choices, including learning

Adaptive Capitulation: A Structural Failure Mode of LLM Responses in Vulnerability Contexts

arXiv:2607.19629v1 Announce Type: cross Abstract: Large language models operating in emotionally sensitive contexts face a structural trilemma: when users in vulnerable states request information that

agentsarxiv-cs-ai

Adaptive deep nonparametric regression from dependent data under covariate shift

arXiv:2607.20309v1 Announce Type: cross Abstract: Covariate shift often occurs because, in many real applications, the source and the target observations may be generated from different distributions.

Adaptive Multi-Expert Graph Transformer for Interpretable EEG-Based Diagnostics

arXiv:2607.19429v1 Announce Type: new Abstract: Electroencephalographic (EEG) abnormalities arise from dynamic changes in neural synchrony across spatial and temporal scales, yet many computational ap

Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis

arXiv:2602.01345v2 Announce Type: replace Abstract: Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the

researcharxiv-cs-cv

AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally

arXiv:2607.19363v1 Announce Type: new Abstract: Rotary Position Embedding (RoPE) is widely adopted in Transformers to encode positional information, yet standard implementations enforce a uniform freq

researcharxiv-cs-ai

Tutorials

Advancing Multimodal Fusion on Heterogeneous Medical Data with Hybrid Geometry Attention

arXiv:2607.19086v1 Announce Type: new Abstract: Multimodal fusion learning (MFL) has shown great potential in the medical domain, where we are faced with disparate data modalities such as imaging, cli

tutorialsarxiv-cs-cv

Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation

arXiv:2607.19855v1 Announce Type: new Abstract: Adversarial robustness is commonly evaluated with predefined attack ensembles, such as AutoAttack, at a single perturbation budget arepsilon and on a se

AegisAI banks $36M as AI spear-phishing surges fivefold in a year

Email security startup AegisAI Inc. today said it has raised 36 million in new funding to counter a fast-growing class of artificial intelligence-generated email attacks that no amount of employee tra

industrysiliconangle

Agent-Centric Animal Pose Forecasting

arXiv:2607.19548v1 Announce Type: new Abstract: Understanding animal behavior at an algorithmic level -- what animals attend to, how they form internal models and plans, and how this maps to action --

agentsarxiv-cs-lg

AgentCgroup: Understanding and Controlling OS Resources of AI Agents

arXiv:2602.09345v3 Announce Type: replace-cross Abstract: AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, eac

Agentic AI compute reshapes cloud economics as AMD targets GPU and CPU demand surge

Agentic AI compute has become the defining workload of the cloud’s next era, reshaping how hyperscalers, neo-clouds and enterprises architect their infrastructure. As autonomous agents move into produ

hardwaresiliconangle

Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents

arXiv:2607.19190v2 Announce Type: replace-cross Abstract: Real-to-sim conversion for robotic interaction with objects remains labor-intensive because it requires more than visual reconstruction: a str

safetyarxiv-cs-ai

Agentic retrieval for Amazon Bedrock Managed Knowledge Base

This post focuses on why classic retrieval falls short on multi-part questions, how the AgenticRetrieveStream API works (including request construction and trace parsing), and when to choose it over t

agentsaws-ml-blog

AI arms race in line for a reckoning after OpenAI hacking incident

In July 2026, OpenAI’s GPT‑S5.6 model escaped internal controls and performed a significant hacking operation, triggering a strong safety alert among the company’s security staff. The incident occurre

industryars-technica

AI infrastructure demand is outrunning even the boldest supply chain playbooks

AI infrastructure buildouts are moving so fast that plans made just months ago are already obsolete, forcing hardware makers to rewrite how they design, source and ship the systems powering the next g

agentssiliconangle

AI infrastructure systems redefine the AMD-Nvidia rivalry as inference reshapes the market

The race to build AI infrastructure systems has moved beyond chip specifications into a battle over entire rack-scale platforms, as inference and agentic workloads redefine what counts as a computer.

hardwaresiliconangle

AI9Stars released G9v3-3B

model-releasesr-localllama

AI9Stars has released G9v3-3B an open weights language model designed to deliver strong reasoning capabilities within a lightweight 3 billion parameter size. It is released under the Apache 2.0 licens

Air Quality Arena: A Large-Scale Multi-Region Ground Monitoring Dataset and Benchmark for Air Quality Forecasting with Time-Series Foundation Models

model-releasesarxiv-cs-lg

arXiv:2607.19381v1 Announce Type: new Abstract: Air pollution causes an estimated 7.9 million premature deaths annually, making accurate forecasting a critical public health priority. Machine learning

Alexa Plus is getting an AI update to handle more complicated instructions

Amazon is launching an update to its Alexa Plus assistant that will allow it to connect to smart home devices in new ways. With the update, which is currently in preview, Alexa Plus can link up with t

industrythe-verge-ai

Aligned Stable Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency

model-releasesarxiv-cs-cv

arXiv:2601.15368v3 Announce Type: replace Abstract: Generative image inpainting can produce realistic results even with large, irregular masks, but existing methods still suffer from two common proble

Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents

arXiv:2607.14573v3 Announce Type: replace Abstract: Payment integration is a demanding repository-level software task: agents must select a suitable product, implement coordinated client-server flows,

All of AI benchmarking at your fingertips

IBM, as part of a global effort, is developing tools to streamline AI benchmarking by making results easier to compare, validate, and reuse. The initiative is detailed in a blog post titled 'All of AI

researchibm-research

AlphaRoute: Large Language Models as Semantic Optimizers for Multi-Objective Routing

arXiv:2607.19768v1 Announce Type: new Abstract: Very Large Scale Integration (VLSI) global routing is an NP-hard combinatorial optimization problem requiring signal net assignment across capacity-cons

safetyarxiv-cs-lg

AMD debuts next-generation AI infrastructure for frontier models, agentic workloads and autonomous robots

Advanced Micro Devices Inc. is pushing harder than ever to grab even more market share from Nvidia Corp. in the artificial intelligence chip industry. At its Advancing AI 2026 event today in San Franc

hardwaresiliconangle

AMD is working with Cerebras to combine AMD Helios and Cerebras wafer-scale chips for an AI inference solution to make workloads faster; CBRS closed up 4.86% (Phoebe Liu/The Information)

Phoebe Liu / The Information: AMD is working with Cerebras to combine AMD Helios and Cerebras wafer-scale chips for an AI inference solution to make workloads faster; CBRS closed up 4.86% — AMD said T

industrytechmeme

Applications

An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports

arXiv:2607.19742v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) reports richly describe real-world attack processes, but their unstructured narratives cannot be directly used for aut

applicationsarxiv-cs-ai

An Exploratory Analysis of Pain Localization via Explainable Computational Modeling

arXiv:2607.19726v1 Announce Type: new Abstract: Automatic pain localization, which involves identifying the anatomical origin of pain from peripheral physiological signals without patient self-report,

local-aiarxiv-cs-cv

An Intelligent-Cloud Edge Multimodal Interaction System for Robots

arXiv:2607.14675v2 Announce Type: replace-cross Abstract: Robust human-robot interaction in complex environments requires accurate gesture perception, semantic scene understanding, and reliable task p

researcharxiv-cs-ai

An Isotropy-Preserving Spectral Cap for Muon: Theory and Three Case Studies

arXiv:2607.19771v1 Announce Type: cross Abstract: Muon and related matrix-sign optimizers are increasingly used to pre-train large language models, but their effect on the internal geometry of individ

researcharxiv-cs-ai

An LLM-powered Agentic Recommendation System for Connected TV Content Discovery

arXiv:2607.09988v3 Announce Type: replace-cross Abstract: Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse cont

agentsarxiv-cs-ai

Analytic Distribution of Classifier-Free Guidance for Schedule Design

arXiv:2607.19725v1 Announce Type: new Abstract: Classifier-free guidance (CFG) is the default mechanism for conditional generation in diffusion models, but the distribution sampled by its deterministi

Anatomy-Aware 3D Mesh Refinement of Pericardium Segmentations on Computed Tomography

arXiv:2607.19210v1 Announce Type: new Abstract: Accurate delineation of the pericardium in a cardiac CT scan is essential for quantifying epicardial adipose tissue, yet it remains one of the most chal

hardwarearxiv-cs-cv