arXiv:2609.03937v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) complements parametric models with retrieved external evidence. The…
Designing lifecycle policies for AgentCore memory
Long-running AI agents accumulate outdated memories that degrade quality and create compliance risk. Learn how to design memory lifecycle policies for…
FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation
arXiv:2609.03889v1 Announce Type: cross Abstract: Contact-rich loco-manipulation requires a bridge between semantic action generation and physical…
OpenAI’s GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt injections
OpenAI’s GPT-6 Astra hallucinates less than its predecessor and blocks 99.99 percent of direct prompt injections. But when attacks are hidden inside…
GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs
arXiv:2609.03892v1 Announce Type: cross Abstract: 3D spatial reasoning underpins understanding and acting in the physical world, yet it remains unreliable…
Training a coding model to paint watercolours with TRL and OpenEnv
This post has no text preview — click the link below to read the original article. This article has been indexed from Hugging Face – Blog Read the original article: Training a coding model to paint watercolours with TRL and…
Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data
arXiv:2609.03878v1 Announce Type: cross Abstract: Reconstruction-based anomaly detectors are accurate but opaque: a deep autoencoder flags a sample…
What will Apple’s John Ternus era look like?
It’s officially the Ternus era at Apple. Tim Cook stepped down as CEO this week, handing the company to former hardware chief John Ternus, whose first…
A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors
arXiv:2609.03884v1 Announce Type: cross Abstract: Modern AI agent harnesses expose lifecycle hooks that bind shell commands to runtime events such as…
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
arXiv:2609.03796v1 Announce Type: cross Abstract: We introduce LLaDA-Image, a unified framework that pairs a 6B Diffusion Transformer (DiT) trained from…
GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History
arXiv:2609.03868v1 Announce Type: cross Abstract: Target-centered gaze interaction requires more than suppressing frame-to-frame fluctuations: target…
The impact of phase information for few-shot fine-grained image classification
arXiv:2609.03829v1 Announce Type: cross Abstract: Few-shot fine-grained image classification (FSFGIC) aims to classify similar images with limited labeled…
AWS Details Open-Source HyperPod InstantStart Control Plane for Agent Ops
Amazon Web Services has detailed HyperPod InstantStart, an open-source control plane that composes Amazon EKS orchestration with the managed capabilities…
Witnesses Explain Anomalies
arXiv:2609.03826v1 Announce Type: cross Abstract: Unsupervised anomaly detection scores each point of an unlabelled, contaminated sample in a single pass,…
Perplexity Open Sources Lily: A Rust + Metal Inference Engine for Qwen3.6-35B-A3B on Apple Silicon
Perplexity has open sourced Lily, the local inference engine behind Hybrid Compute in Perplexity Computer. Built in Rust with custom Metal kernels for one…
Free Pause Tokens
arXiv:2609.03807v1 Announce Type: cross Abstract: A free pause token gives a language model extra compute to form each next-token prediction (as a pause,…
AI News Brief Hourly Summary 2026-09-04 19h : 19 posts
19 posts published in the last hour 16:34ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation 16:34Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod 16:34Apple’s Ternus era begins as Nvidia bets on the whole AI stack 16:33Microsoft…
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation
arXiv:2609.03756v1 Announce Type: cross Abstract: We present ENEAS, a unified, text-promptable method for instance tracking and semantic discovery.…