Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
arXiv:2603.11149v1 Announce Type: new Abstract: Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law framework...
Huntington Disease Automatic Speech Recognition with Biomarker Supervision
arXiv:2603.11168v1 Announce Type: new Abstract: Automatic speech recognition (ASR) for pathological speech remains underexplored, especially for Huntington's disease (HD), where irregular timing, unstable phonation, and articulatory distortion challenge current models. We present a systematic HD-ASR study using a high-fidelity clinical...
Representation Finetuning for Continual Learning
arXiv:2603.11201v1 Announce Type: new Abstract: The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams. While pre-trained models have shown powerful performance in continual learning, they still require finetuning to adapt effectively...
Beyond the Class Subspace: Teacher-Guided Training for Reliable Out-of-Distribution Detection in Single-Domain Models
arXiv:2603.11269v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection methods perform well on multi-domain benchmarks, yet many practical systems are trained on single-domain data. We show that this regime induces a geometric failure mode, Domain-Sensitivity Collapse (DSC): supervised training compresses features...
Single molecule localization microscopy challenge: a biologically inspired benchmark for long-sequence modeling
arXiv:2603.11296v1 Announce Type: new Abstract: State space models (SSMs) have recently achieved strong performance on long sequence modeling tasks while offering improved memory and computational efficiency compared to transformer based architectures. However, their evaluation has been largely limited to synthetic...
On the Robustness of Langevin Dynamics to Score Function Error
arXiv:2603.11319v1 Announce Type: new Abstract: We consider the robustness of score-based generative modeling to errors in the estimate of the score function. In particular, we show that Langevin dynamics is not robust to the L^2 errors (more generally L^p errors)...
Ensuring Safety in Automated Mechanical Ventilation through Offline Reinforcement Learning and Digital Twin Verification
arXiv:2603.11372v1 Announce Type: new Abstract: Mechanical ventilation (MV) is a life-saving intervention for patients with acute respiratory failure (ARF) in the ICU. However, inappropriate ventilator settings could cause ventilator-induced lung injury (VILI). Also, clinicians workload is shown to be directly...
Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks
arXiv:2603.11487v1 Announce Type: new Abstract: Transformers often display an attention sink: probability mass concentrates on a fixed, content-agnostic position. We prove that computing a simple trigger-conditional behavior necessarily induces a sink in softmax self-attention models. Our results formalize a familiar...
How to watch Jensen Huang’s Nvidia GTC 2026 keynote
GTC — which stands for GPU Technology Conference — is Nvidia's flagship annual event, where the chipmaker typically uses the spotlight to announce new products, champion partnerships, and lay out its vision for the future of computing. Huang's keynote will...
Sales automation startup Rox AI hits $1.2B valuation, sources say
Rox, founded in 2024 by the former chief growth officer of New Relic, offers an AI-native alternative to CRM tools.
Facebook Marketplace now lets Meta AI respond to buyers’ messages
When buyers inquire about an item’s availability, sellers can use Meta AI to automatically draft replies using information from their listing, such as the description, availability, pickup location, and price.
Tinder tries to lure people back to online dating with IRL events, virtual speed dating
Tinder just got a major revamp as it attempts to reengage its user base and attract younger daters. This includes in-person events, AI enhancements, and even virtual speed dating.
Atlassian follows Block’s footsteps and cuts staff in the name of AI
Atlassian laid off 10% of its workforce, around 1,600 people, as the company looks to funnel more funds to AI.
Bumble introduces an AI dating assistant, ‘Bee’
Bumble's new AI assistant Bee will move the dating app beyond the swipe by matching people based on compatibility and goals.
A writer is suing Grammarly for turning her and other authors into ‘AI editors’ without consent
Journalist Julia Angwin is leading a class action lawsuit against Grammarly for violating her privacy and publicity rights.
Gumloop lands $50M from Benchmark to turn every employee into an AI agent builder
As companies race to adopt AI, Benchmark general partner Everett Randle believes the key to success lies in empowering every worker with AI superpowers, and Gumloop’s intuitive agent builder is an example of the kind of tool that will unlock...
Alexa+ gets a new ‘adults only’ personality option that curses but won’t do NSFW content
The new Sassy style can curse and roast you, but the fun ends there.
Wonderful raises $150M Series B at $2B valuation
The funding round, led by Insight Partners, comes just four months after Wonderful raised a $100 million Series A.
Google Maps is getting an AI ‘Ask Maps’ feature and upgraded ‘immersive’ navigation
The tech giant says the "Immersive Navigation" launch is the biggest update to Maps in over a decade.
Hybrid Self-evolving Structured Memory for GUI Agents
arXiv:2603.10291v1 Announce Type: new Abstract: The remarkable progress of vision-language models (VLMs) has enabled GUI agents to interact with computers in a human-like manner. Yet real-world computer-use tasks remain difficult due to long-horizon workflows, diverse interfaces, and frequent intermediate errors....
FERRET: Framework for Expansion Reliant Red Teaming
arXiv:2603.10010v1 Announce Type: cross Abstract: We introduce a multi-faceted automated red teaming framework in which the goal is to generate multi-modal adversarial conversations that would break a target model and introduce various expansions that would result in more effective and...
AraModernBERT: Transtokenized Initialization and Long-Context Encoder Modeling for Arabic
arXiv:2603.09982v1 Announce Type: cross Abstract: Encoder-only transformer models remain widely used for discriminative NLP tasks, yet recent architectural advances have largely focused on English. In this work, we present AraModernBERT, an adaptation of the ModernBERT encoder architecture to Arabic, and...
Empathy Is Not What Changed: Clinical Assessment of Psychological Safety Across GPT Model Generations
arXiv:2603.09997v1 Announce Type: cross Abstract: When OpenAI deprecated GPT-4o in early 2026, thousands of users protested under #keep4o, claiming newer models had "lost their empathy." No published study has tested this claim. We conducted the first clinical measurement, evaluating three...
Agentic Control Center for Data Product Optimization
arXiv:2603.10133v1 Announce Type: new Abstract: Data products enable end users to gain greater insights about their data by providing supporting assets, such as example question-SQL pairs which can be answered using the data or views over the database tables. However,...
The DMA Streaming Framework: Kernel-Level Buffer Orchestration for High-Performance AI Data Paths
arXiv:2603.10030v1 Announce Type: cross Abstract: AI transport libraries move bytes efficiently, but they commonly assume that buffers are already correctly allocated, placed, shared, registered, and safe under completion and teardown pressure. This paper presents dmaplane, a Linux kernel module that...
GATech at AbjadGenEval Shared Task: Multilingual Embeddings for Arabic Machine-Generated Text Classification
arXiv:2603.10007v1 Announce Type: new Abstract: We present our approach to the AbjadGenEval shared task on detecting AI-generated Arabic text. We fine-tuned the multilingual E5-large encoder for binary classification, and we explored several pooling strategies to pool token representations, including weighted...
Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights
arXiv:2603.10033v1 Announce Type: new Abstract: Graph foundation models (GFM) aim to acquire transferable knowledge by pre-training on diverse graphs, which can be adapted to various downstream tasks. However, domain shift in graphs is inherently two-dimensional: graphs differ not only in...
TriageSim: A Conversational Emergency Triage Simulation Framework from Structured Electronic Health Records
arXiv:2603.10035v1 Announce Type: new Abstract: Research in emergency triage is restricted to structured electronic health records (EHR) due to regulatory constraints on nurse-patient interactions. We introduce TriageSim, a simulation framework for generating persona-conditioned triage conversations from structured records. TriageSim enables...
The Generation-Recognition Asymmetry: Six Dimensions of a Fundamental Divide in Formal Language Theory
arXiv:2603.10139v1 Announce Type: new Abstract: Every formal grammar defines a language and can in principle be used in three ways: to generate strings (production), to recognize them (parsing), or -- given only examples -- to infer the grammar itself (grammar...
Sabi\'a-4 Technical Report
arXiv:2603.10213v1 Announce Type: new Abstract: This technical report presents Sabi\'a-4 and Sabiazinho-4, a new generation of Portuguese language models with a focus on Brazilian Portuguese language. The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and...