Knowledge catalogue
arXiv:2607.00457v1 Announce Type: new Abstract: Embodied agents operating in the real world require multi-scale reasoning and knowledge adaptation as conditions change. We identify two challenges in a
PamStealer is a macOS infostealer disguised as the legitimate Maccy clipboard manager that uses a two-stage attack chain to silently harvest data and clipboard contents while evading detection. The ma
arXiv:2607.00248v1 Announce Type: new Abstract: We present Seed2.0, a model series that takes a meaningful step toward solving complex, real-world tasks. Our approach begins with identifying users' ge
arXiv:2607.01136v1 Announce Type: cross Abstract: Agent skills package reusable operational knowledge for Large Language Model (LLM) agents, yet as they grow in scope, they become dependency-bearing a
arXiv:2607.00063v1 Announce Type: cross Abstract: This paper studies how spectral geometry emerges in quantum learning models and how it can be diagnosed with physically grounded probes. In graph-regu
arXiv:2603.00198v2 Announce Type: replace-cross Abstract: Token reduction accelerates long-video vision--language models (VLMs), but existing methods target Transformers, where reduction is treated as
arXiv:2607.00047v1 Announce Type: cross Abstract: Vertigo Vertigo is a scene-for-scene AI reconstruction of Hitchcock's Vertigo (1958), generated from only 2.78% of the original film's frames. Using t
arXiv:2606.31420v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) enables models trained on a source domain to adapt online to unlabeled test data under distribution shifts. While recent TTA
arXiv:2602.20055v2 Announce Type: replace-cross Abstract: Robot navigation typically assumes an obstacle-free path exists between start and goal. In real environments, however, clutter may block all r
arXiv:2606.31033v1 Announce Type: new Abstract: In this paper, we propose CORTEX, a token-level hallucination detection method for Retrieval-Augmented Generation (RAG). In long-form RAG outputs, hallu
arXiv:2603.13402v3 Announce Type: replace Abstract: Current text-to-video models can make individual frames look convincing while still getting simple interactions wrong: objects move before contact,
arXiv:2606.31644v1 Announce Type: new Abstract: As large language models take on morally consequential roles in healthcare, legal, and hiring contexts, we need to examine whether their ethical behavio
arXiv:2606.31933v1 Announce Type: new Abstract: We introduce VidPair-Halluc, a new benchmark for evaluating video hallucination in large video models (LVMs) under rigorous and controlled conditions. U
arXiv:2606.31830v1 Announce Type: new Abstract: Most end-to-end autonomous driving methods rely solely on instantaneous sensor observations, limiting them to reactive behavior without the anticipatory
Significant contributors to this article include Sneha Aradhey, Software Engineer, Google Kubernetes Engine, and Michael MacDonald, Sr Software Engineer, Google Cloud Managed Lustre. Enterprise produc
arXiv:2602.15029v3 Announce Type: replace-cross Abstract: The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a cir
arXiv:2606.31339v1 Announce Type: new Abstract: Agentic artificial intelligence is increasingly used to decompose industrial tasks, propose robot actions, and adapt execution plans in dynamic cyber-ph
arXiv:2606.30989v1 Announce Type: cross Abstract: Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs
arXiv:2606.31410v1 Announce Type: new Abstract: Graphical user interface (GUI) agents build on vision-language models to complete user tasks end-to-end in real applications through interface actions s
arXiv:2606.28525v1 Announce Type: cross Abstract: Fine-tuning on harmless data can partially undo behaviors acquired earlier in training. Safety can erode under benign post-alignment updates, unlearne
arXiv:2508.02923v3 Announce Type: replace Abstract: Maximum A Posteriori (MAP) estimation is a cornerstone framework for blind inverse problems, where an image and a forward operator are jointly estim
arXiv:2606.28345v1 Announce Type: cross Abstract: LLM-governed social robots increasingly decide who receives real-world assistance first. As prioritization norms vary across cultures by age, status,
arXiv:2606.28753v1 Announce Type: cross Abstract: Continuous-recording surveillance systems face a storage problem that codec tuning alone cannot fully solve: even at aggressive CRF settings, a static
arXiv:2511.05852v4 Announce Type: replace-cross Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs). Meanwhile, fine-tuning remain
arXiv:2606.30479v1 Announce Type: cross Abstract: Mitigating an observed adversary in an enterprise network typically takes weeks of expert work: an analyst derives a mitigation tailored to that adver
arXiv:2606.28720v1 Announce Type: new Abstract: Lifelong scene mapping under rigid object rearrangement remains a fundamental challenge in robotics. While 3D Gaussian Splatting (3DGS) enables high-fid
arXiv:2606.28471v1 Announce Type: new Abstract: Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it
arXiv:2606.28524v1 Announce Type: new Abstract: Recent work suggests that Large Language Models (LLMs) are sensitive to the belief states of agents described by text, as measured by the false belief t
arXiv:2603.28691v2 Announce Type: replace Abstract: Open-Vocabulary Object Navigation (OVON) requires an embodied agent to locate a language-specified target in unknown environments. Many zero-shot me
arXiv:2606.30185v1 Announce Type: new Abstract: Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools. We present Dynamo, a train
arXiv:2606.30344v1 Announce Type: cross Abstract: Visual classifiers can achieve high matched-distribution accuracy while relying on low-level cues that fail under conflict or suppression. We test whe
arXiv:2606.29031v1 Announce Type: cross Abstract: In regulated domains such as banking and healthcare, where privacy constraints make real speech costly to collect and retain, synthetic speech from mo
arXiv:2606.29139v1 Announce Type: new Abstract: We study how the next-token prediction of an autoregressive Transformer language model changes under small perturbations of earlier input token embeddin
arXiv:2606.28781v1 Announce Type: new Abstract: Every existing vector database and agent memory framework treats memory as passive storage that agents query explicitly. No system propagates knowledge
arXiv:2505.20935v3 Announce Type: replace Abstract: Recent open-weight text-to-image (T2I) diffusion models still struggle with multi-instance prompts, often omitting or merging instances and mixing s
arXiv:2606.29824v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires con
// Neural procedural memory // Good paper on agent memory beyond prompt retrieval. NPM stores procedural skills as activation steering vectors distilled from contrastive historical experience. Textual
arXiv:2606.29971v1 Announce Type: new Abstract: A growing body of work suggests that the reasoning capabilities of large language models are largely latent in their base form, with post-training prima
arXiv:2606.28867v1 Announce Type: new Abstract: Creative Commons licenses dominate African NLP corpus releases, but their compatibility rules are rarely applied. CC-BY-SA and CC-BY-NC cannot be combin
arXiv:2606.30068v1 Announce Type: new Abstract: Joint-embedding predictive (JEPA-style) objectives learn representations by predicting future latents. In doing so they can discard features that are ex
Project gallery and whitepaper: https://research.nvidia.com/labs/gear/aspire/ ASPIRE is a great collaboration between NVIDIA GEAR lab, UMich, Berkeley, and CMU. Kudos to all the coauthors who pour the
arXiv:2606.30639v1 Announce Type: new Abstract: World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unrel
arXiv:2606.29713v1 Announce Type: cross Abstract: Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers
arXiv:2606.30201v1 Announce Type: cross Abstract: Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical
arXiv:2606.30481v1 Announce Type: cross Abstract: Current large language models are extraordinary statistical engines. They compress vast amounts of text into useful patterns and can explain science,
arXiv:2602.13792v2 Announce Type: replace Abstract: Artificial intelligence built on large foundation models has transformed language understanding, computer vision, and reasoning, yet these systems r
arXiv:2606.29247v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models represent a promising direction for embodied intelligence in surgical robotics. Despite the prevalence of VLA benchm
arXiv:2606.29567v1 Announce Type: cross Abstract: LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control. When those queries cont
arXiv:2511.17649v4 Announce Type: replace-cross Abstract: Tangible control interfaces (TCIs), such as appliance panels, remotes, elevators, and embedded GUIs, are a fundamental component of everyday h
arXiv:2603.02491v3 Announce Type: replace-cross Abstract: As artificial agents become increasingly capable, what internal structure is necessary for an agent to act competently under uncertainty? Clas
arXiv:2606.29791v1 Announce Type: cross Abstract: Outlier detection (OD) aims to identify anomalous instances by learning the underlying structure of normal data (inliers), and is particularly challen
arXiv:2606.27951v1 Announce Type: cross Abstract: AI agents are promising tools that can act as flexible behavioral nudges to enhance human cooperation in addressing large-scale societal problems. How
arXiv:2606.28049v1 Announce Type: new Abstract: In recent years, multimodal large language models (MLLMs) have shown strong potential for embodied intelligence, yet their ability to maintain geometric
arXiv:2606.27715v1 Announce Type: new Abstract: We show that for tall matrix parameters, like projection matrices in the MLP layers, the Muon update can have row norms that are arbitrarily non-uniform
arXiv:2602.16065v2 Announce Type: replace-cross Abstract: As artificial intelligence (AI)-generated content proliferates, models are increasingly trained on their own outputs, risking progressive degr
Welcome to the second Cloud CISO Perspectives for June 2026. Today, we’re discussing how we use AI to chart a path to autonomous software development lifecycle security.As with all Cloud CISO Perspect
arXiv:2510.09685v2 Announce Type: replace-cross Abstract: Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly ad
arXiv:2606.28002v1 Announce Type: cross Abstract: Insurance fraud imposes substantial financial losses and operational inefficiencies, raising premiums and impacting trust among legitimate policyholde
arXiv:2601.18197v2 Announce Type: replace Abstract: While Large Vision-Language Models (LVLMs) have significantly advanced GUI agents' capabilities in parsing textual instructions, interpreting screen
arXiv:2511.11266v4 Announce Type: replace Abstract: Vision-language models have recently emerged as promising planners for autonomous driving, where success hinges on topology-aware reasoning over spa