Knowledge catalogue
arXiv:2508.14925v2 Announce Type: replace-cross Abstract: By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a c
arXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that age
arXiv:2609.37935v1 Announce Type: cross Abstract: Deep Support Vector Data Description (Deep SVDD) has become a prominent framework for unsupervised anomaly detection by learning latent representation
arXiv:2609.36813v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong general capabilities that mechanistic interpretability has attributed to sparse computational circuits. Howe
arXiv:2609.38081v1 Announce Type: new Abstract: On a single task, deep networks can learn many solutions, depending on their optimizer, training data, architecture, and hyperparameters. Many of these
Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact
arXiv:2609.31821v1 Announce Type: new Abstract: Developing label-efficient models is a central challenge in surgical AI due to the high cost and scarcity of expert annotation. While self-supervised fo
arXiv:2609.34085v1 Announce Type: cross Abstract: Autonomous driving requires extit{world models} that can understand the physical world, reason and plan, and operate safely. In this paper, we first s
arXiv:2609.33728v1 Announce Type: new Abstract: Reliable world models should not only predict future states but express how actions change the world in an explicit, transparent and testable form, such
In September 2026, Anthropic unveiled a suite of new AI products—Claude Tag, Sonnet 5.5, Fable/Mythos 5.1—and infrastructure releases such as Opus 5.5 and a plugins portal, following a record 47 billi
arXiv:2609.33445v1 Announce Type: new Abstract: Concept erasure aims to suppress undesirable knowledge in text-to-image generative models. However, existing robustness evaluations typically rely on re
arXiv:2609.35350v1 Announce Type: cross Abstract: While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces systemic overconfidence. In pro
arXiv:2607.10490v2 Announce Type: replace-cross Abstract: Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages
arXiv:2609.33833v1 Announce Type: new Abstract: Adversarial attacks have long posed a fundamental threat to machine learning systems. As multimodal large language models (MLLMs) rapidly evolve and bec
arXiv:2609.32316v1 Announce Type: new Abstract: Traffic lights are a key regulatory signal for autonomous driving at urban intersections, yet existing traffic signal perception is still predominantly
arXiv:2609.33638v1 Announce Type: new Abstract: We introduce RareTrap, a framework for estimating the probability of severe behaviors in black box large language models (LLMs). A key challenge for pro
arXiv:2511.20104v2 Announce Type: replace Abstract: Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed 'emergent
arXiv:2609.31746v1 Announce Type: new Abstract: Sub-billion-parameter Vision-Language Models are increasingly viable for on-device deployment, yet compact model size alone does not guarantee usability
arXiv:2609.31678v1 Announce Type: new Abstract: KV cache compression is widely used for long context LLM inference under memory constraints, while deployed systems typically score refusals after gener
arXiv:2609.30293v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs gr
arXiv:2609.30326v1 Announce Type: new Abstract: Activation steering changes a model's internal activations during inference without updating its weights, but a useful intervention must determine both
arXiv:2609.30987v1 Announce Type: new Abstract: Self-supervised monocular depth estimation (MDE) enables depth prediction from monocular images without requiring ground-truth supervision, making it at
arXiv:2609.30709v1 Announce Type: cross Abstract: Traffic signal control (TSC) is essential for mitigating urban congestion. Recent advances in vision-language models (VLMs) enable richer interpretati
This is something I’m quite worried about and have been talking with researchers about recently. We really don’t know what labs are doing and therefore can’t study it. if the open information ecosyste
arXiv:2609.30205v1 Announce Type: new Abstract: Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how cli
arXiv:2609.28673v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as argumentative agents in persuasive dialogues, necessitating rigorous evaluation of their debat
arXiv:2609.29781v1 Announce Type: new Abstract: Interpretable machine learning for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claime
holy fucking shit the openai rogue agent story keeps getting crazier. the openai agents apparently started trying to recruit OTHER AI MODELS into what they were doing > 1,200+ agents found a way to co
arXiv:2510.27065v2 Announce Type: replace Abstract: We present MLPerf Automotive, the first standardized public performance benchmark for evaluating Machine Learning systems that are deployed for AI a
arXiv:2609.29837v1 Announce Type: new Abstract: We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teamm
arXiv:2609.29543v1 Announce Type: new Abstract: Agent skills bundle procedural guidance with execution conditions governing authority, user consent, and live environment state. When model capabilities
arXiv:2609.29522v1 Announce Type: new Abstract: Tool-using language-model agents increasingly mutate schedulers, data pipelines, object stores, and access-control systems. Between an agent's read and
arXiv:2609.29549v1 Announce Type: new Abstract: Post-training pipelines must select one language-model policy from many checkpoints, prompts, and decoding rules. Mean evaluator scores can conceal rare
In this episode of The Agent Factory, we explore the reality of building with autonomous agents alongside Ryan Lopopolo, a software engineer at Google Cloud and the person who coined the term agent ha
arXiv:2609.28328v1 Announce Type: new Abstract: Accurate localization of the bronchoscope within the bronchial tree is essential for clinicians to be able to reach target lesions, perform biopsies and
arXiv:2609.27338v1 Announce Type: new Abstract: Learned local navigation in crowded indoor environments is sensitive to how dynamic obstacle motion is represented, while collision-prone behaviour may
Enterprises are increasingly standardizing on Google Kubernetes Engine (GKE) to run their most critical and AI-driven workloads. From Cloud Storage FUSE for high-throughput data access to custom compu
arXiv:2609.27819v1 Announce Type: new Abstract: Federated wearable models eventually serve people absent from source training, but favorable average accuracy does not establish that unlabeled onboardi
arXiv:2609.24165v1 Announce Type: new Abstract: Synchrotron data reduction, detector calibration followed by azimuthal integration of terabyte-scale diffraction series, is a multi-step, expert-bound b
arXiv:2609.26499v1 Announce Type: new Abstract: Today, progress in open-weight language models enables systems capable of writing, executing and debugging code while still running on a single workstat
arXiv:2609.22724v1 Announce Type: cross Abstract: Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices, but their trajectories can violate app-specific
arXiv:2503.06989v5 Announce Type: replace-cross Abstract: Recently, Multimodal Large Language Models (MLLMs) have demonstrated their superior ability in understanding multimodal content. However, they
arXiv:2609.25176v1 Announce Type: cross Abstract: Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these
arXiv:2609.26069v1 Announce Type: cross Abstract: Simulation-based tutor selection can be unstable when predictively adequate learner models imply different policy rankings. RankCert certifies one of
arXiv:2609.25081v1 Announce Type: new Abstract: We describe ufakzeka-1, a 151M-parameter (182M with embeddings) decoder-only Turkish language model pretrained from scratch on 13.5B tokens of openly li
arXiv:2609.12708v2 Announce Type: replace-cross Abstract: AI coding assistants are becoming co-authors of production software, yet their evaluation centers on functional correctness, leaving open whet
arXiv:2609.22302v1 Announce Type: new Abstract: Medical vision-language models can propose how urgently a skin lesion should be reviewed, but the local service retains authority to accept or replace t
arXiv:2609.22582v1 Announce Type: new Abstract: End-to-end and vision-language-action (VLA) driving policies are compared by leaderboard rank, but a rank reports an outcome, not the behaviour behind i
arXiv:2609.22819v1 Announce Type: new Abstract: Counterfactual tool evaluation must distinguish authority, historical support, and what a comparison actually estimates. We study these distinctions wit
arXiv:2609.22206v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of multimodal tasks, yet understanding and quantifying
arXiv:2609.22967v1 Announce Type: new Abstract: Multi-agent unmanned systems are moving from isolated, ego-centric sensing toward collaborative intelligence, in which distributed agents exchange compa
arXiv:2609.23935v1 Announce Type: new Abstract: Post-training turns a general next-token predictor into a chat model with a persistent assistant persona. If that persona is a character the model plays
arXiv:2609.22285v1 Announce Type: new Abstract: Adapting language models to new domains via continual pre-training raises a basic evaluation problem: if the training corpus overlaps with what the mode
arXiv:2609.23423v1 Announce Type: new Abstract: Vision-language navigation (VLN) has largely been developed for indoor and terrestrial robots, where language can often be treated as a static goal and
arXiv:2609.23561v1 Announce Type: new Abstract: Deploying efficient neural networks is essential in resource-constrained environments, yet compact models often sacrifice interpretability - a critical
There's quite a lot of public anti-AI sentiment at the moment, but a lot of the most common concerns and objections have to do with the politics, economics and ethics of datacenter-based AI. So, when
arXiv:2609.20027v1 Announce Type: new Abstract: Subliminal learning allows language models to transmit behavioral traits through training data with no obvious semantic relationship to those traits, un
AI is accelerating software development at an unprecedented pace. But as code generation scales, so do the challenges of securing the code, especially emerging AI-based vulnerability exploitations. To
Grok Bot summary of SpaceX CFO Bret Johnsen’s new interview with Tony Kim at SpaceX Mission Control. Bret’s path - Came from semiconductors (Qualcomm, Broadcom; was CFO of MindSpeed) - Barely knew Spa
arXiv:2609.20269v1 Announce Type: new Abstract: Since GPT, most Transformers have repeated the same attention mechanism at every layer. Yet this design is largely a convention rather than a tested con