PlanFlip: Attacking Multi-Agent LLM Systems via Planning-Phase Prompt Injection
arXiv:2607.16199v1 Announce Type: new
Abstract: Multi-agent LLM systems increasingly rely on a Planner to decompose goals into sub-task sequences that downstream Executor and Critic agents execute and audit. We identify the planning phase as a critical attack surface: a single injection into the Pl...
Some Large Language Models Exhibit Consistent Risk Attitudes
arXiv:2607.16197v1 Announce Type: new
Abstract: As artificial intelligence systems are deployed in open-ended, high-stakes settings, a critical dimension remains unmeasured: how perceived risk is translated into action. We test whether large language models (LLMs) exhibit systematic and consistent ...
Design and Validation of a Lightweight 1D CNN for Affective Touch Classification in Soft Plush Companions
arXiv:2607.16196v1 Announce Type: new
Abstract: Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies, yet their deformability and multichannel tactile sensing complicate the robust interpretation of human affect. This study pres...
Rater State Bias in RLHF Preference Data: An Audit Framework
arXiv:2607.16195v1 Announce Type: new
Abstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs, but they may also reflect the rater's state during annotation. Under sustained stressful o...
LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats
arXiv:2607.16227v1 Announce Type: new
Abstract: LLMs are increasingly deployed in security-critical systems across healthcare, finance, education, and decision support, yet their inability to forget creates serious cybersecurity, privacy, and safety risks. Sensitive personal information, copyrighte...
Fully-sensorized smart-eyewear platform for on-device Machine Learning
arXiv:2607.16222v1 Announce Type: new
Abstract: This paper presents ARGO, a smart eyewear platform designed to bridge ergonomic comfort, high computational throughput, and energy efficiency. Unlike cloud-dependent solutions, ARGO leverages the STM32N6 microcontroller and its integrated Neural Proce...
DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth
arXiv:2607.16203v1 Announce Type: new
Abstract: Document parsing is a foundational step for document understanding tasks such as visual question answering and key information extraction, as it transforms unstructured scanned images into structured representations by extracting textual, visual, and ...
Accelerating Text-to-Video Generation with Calibrated Sparse Attention
Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a significant fraction of token-to-token connections consistently yiel...
Environment-free Synthetic Data Generation for API-Calling Agents
Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories. However, collecting such data at scale typically requires fully implemented environments with executable APIs and realistic, pre-populated backend databases, creating a major bottleneck for s...
Alibaba’s Tongyi Lab Releases Qwen-Audio-3.0-TTS, a Hosted Text-to-Speech Model in Flash and Plus Tiers Across 16 Languages
Alibaba’s Tongyi Lab has released Qwen-Audio-3.0-TTS, a production-oriented text-to-speech (TTS) system. The model ships in two variants from the same lineage. Flash targets real-time interaction. Plus targets high-quality generation. Both are delivered as hosted models through Alibaba Cloud Model S...
AI’s most important protocol is getting a little bit easier to use
The Model Context Protocol (MCP) is one of the basic building blocks of AI interoperability, giving AI models a secure way to access external data sources and services. It’s the plumbing that lets a chatbot reach into your calendar, your database, or your internal tools, instead of engineers buildin...
China’s AI models have Trump’s AI world at war with itself
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Over the weekend, several current and former advisors to President Donald Trump on AI publicly lobbed insults at the country’s leading AI companies. David Sacks, ...
Loop Engineering with Adaptive Parsing in Action: Parsing Flat Tables with Azure and Figures with a Vision LLM
Enterprise Document Intelligence [Vol.1 #10B] - The LLM as last line of defence, then two real escalations walked end to end: a flat table to Azure, a figure to a vision model
The post Loop Engineering with Adaptive Parsing in Action: Parsing Flat Tables with Azure and Figures with a Vision LLM appe...
Top 5 MCP Servers for High-Performance Agentic Development
Here are five that are genuinely worth wiring into a high-performance agent development setup, chosen for what they do to an agent's actual capability rather than their star count.
Somewhere in a Singapore data center, a bank is paying for eight H100s that spend most of the night waiting. The cluster was bought for good reasons (discomfort with customer documents leaving the building, a strategy team’s aversion to lock-in), so the bank secured its own sovereign compute. Now th...
Bristol Myers Squibb Building Life Science Industry’s Most Advanced AI Factory on NVIDIA Vera Rubin
Erin Davis calls it the “SuperDuperPOD.” That’s two things in one name: pharmaceutical giant Bristol Myers Squibb (BMS) already runs one of the largest AI clusters in life sciences, with serious results to show for it. And they’re doubling down. BMS announced today it is deploying its second NVIDIA ...
Safety and alignment in an era of long-horizon models
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.