Knowledge catalogue
arXiv:2604.05350v2 Announce Type: replace Abstract: Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user repo
arXiv:2604.07965v1 Announce Type: new Abstract: Model editing aims to update knowledge to add new concepts and change relevant information without retraining. Lifelong editing is a challenging task, p
arXiv:2604.07147v1 Announce Type: cross Abstract: Large language models produce repetitive output when prompted independently across many batches, a phenomenon we term cross-batch mode collapse: the p
arXiv:2510.14509v3 Announce Type: replace-cross Abstract: The rapid advancement in large language models (LLMs) has demonstrated significant potential in End-to-End Software Development (E2ESD). Howev
arXiv:2604.08106v1 Announce Type: new Abstract: Micro-expression recognition can obtain the real emotion of the individual at the current moment. Although deep learning-based methods, especially Trans
arXiv:2510.04641v3 Announce Type: replace Abstract: Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a re
arXiv:2604.07997v1 Announce Type: new Abstract: Incremental 3D object perception is a critical step toward embodied intelligence in dynamic indoor environments. However, existing incremental 3D detect
For anyone building agentic workflows: the real bottleneck isn't the model, it's the harness. Open standards are a must, not just for flexibility, but to ensure we actually own the long-term memory th
arXiv:2604.06664v1 Announce Type: cross Abstract: Modern LLM service providers increasingly rely on autoscaling and parallelism reconfiguration to respond to rapidly changing workloads, but cold-start
Nous Research draws its name from the ancient Greek concept of *nous* — the faculty of directly perceiving truth, reason, and divine reality — while its flagship model series, **Hermes**, is named ...
FLORA built FAUNA, a long-running creative agent that turns ideas into visual workflows on a digital canvas, allowing designers to describe goals like campaign visuals or moodboards and have the ag...
arXiv:2604.07108v1 Announce Type: cross Abstract: Catastrophic forgetting is not an engineering failure. It is a mathematical consequence of storing knowledge as global parameter superposition. Existi
arXiv:2510.07809v4 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) empower autonomous mobile agents, yet their security under realistic mobile deployment constraints remain
Nous Research is hosting a **Hermes Agent Jam** on **Tuesday, April 14th, 2026 at 4PM EST** in the Nous Discord server, featuring presentations and a Q&A session with the Nous Research team. The ev...
Migrating your existing application load balancer infrastructure from an on-premises hardware solution to Cloud Load Balancing offers substantial advantages in scalability, cost-efficiency, and tight
arXiv:2604.07121v1 Announce Type: cross Abstract: In the human-AI collaboration area, the context formed naturally through multi-turn interactions is typically flattened into a chronological sequence
arXiv:2604.07722v1 Announce Type: new Abstract: In computational cytology, detecting malignancy on whole-slide images is difficult because malignant cells are morphologically diverse yet vanishingly r
arXiv:2604.07788v1 Announce Type: cross Abstract: We introduce PeReGrINE, a benchmark and evaluation framework for personalized review generation grounded in graph-structured user--item evidence. PeRe
arXiv:2604.06865v1 Announce Type: cross Abstract: Physical adversarial attacks are increasingly studied in settings that resemble deployed surveillance systems rather than isolated image benchmarks. I
arXiv:2512.18662v2 Announce Type: replace-cross Abstract: End-to-end (E2E) autonomous driving models that take only camera images as input and directly predict a future trajectory are appealing for th
arXiv:2505.24848v4 Announce Type: replace Abstract: To enable egocentric contextual AI in always-on smart glasses, it is crucial to be able to keep a record of the user's interactions with the world,
arXiv:2604.07595v1 Announce Type: cross Abstract: Language model agents reason from scratch on every query: each time an agent retrieves evidence and deliberates, the chain of thought is discarded and
arXiv:2601.04268v2 Announce Type: replace Abstract: Weather and climate models rely on parametrisations to represent unresolved sub-grid processes. Traditional schemes rely on fixed coefficients that
arXiv:2604.06996v1 Announce Type: cross Abstract: LLM-as-a-judge has become the de facto approach for evaluating LLM outputs. However, judges are known to exhibit self-preference bias (SPB): they tend
arXiv:2509.26036v3 Announce Type: replace Abstract: While Contrastive Language-Image Pretraining (CLIP) excels at zero-shot tasks by aligning image and text embeddings, its performance in few-shot cla
arXiv:2604.06436v2 Announce Type: cross Abstract: We prove that no continuous, utility-preserving wrapper defense-a function D: Xo X that preprocesses inputs before the model sees them-can make al
arXiv:2604.07921v1 Announce Type: new Abstract: We present a large-scale survey of sustainability communication and motivation in robotics research. Our analysis covers nearly 50,000 open-access paper
arXiv:2604.06200v1 Announce Type: cross Abstract: Designing project-based learning (PBL) demands managing highly interdependent components, a task that both traditional linear tools and purely convers
arXiv:2604.06689v1 Announce Type: new Abstract: Accurate classification requires not only high predictive accuracy but also well-calibrated confidence estimates. Yet, modern deep neural networks (DNNs
arXiv:2604.07266v1 Announce Type: new Abstract: Evaluating robustness under temporal distribution shift remains an open challenge. Existing metrics quantify the average decline in performance, but fai
Custom GPTs are tailored versions of ChatGPT that users can configure for specific tasks, roles, or workflows by setting instructions, uploading proprietary knowledge files, and enabling capabiliti...
Want to know the latest from Google Cloud? Find it here in one handy location. Check back regularly for our newest updates, announcements, resources, events, learning opportunities, and more. Tip: Not
arXiv:2604.07957v1 Announce Type: cross Abstract: Vision-language models (VLMs) and generative world models are opening new opportunities for embodied navigation. VLMs are increasingly used as direct
'Harnesses are intimately tied to memory, which means that by choosing an open harness you are choosing to own your memory, and not have it be locked into a proprietary harness or tied to a single mod
ALTK-Evolve, published by IBM Research, is a memory system for AI agents that enables on-the-job learning by helping agents improve over time, learning from and using guidelines generated from pre...
Meta announced Muse Spark today, their first model release since Llama 4 almost exactly a year ago. It's hosted, not open weights, and the API is currently 'a private API preview to select users', but
In the world of AI/ML, data is the fuel that drives training and inference workloads. For Google Kubernetes Engine (GKE) users, Cloud Storage FUSE provides high-performance, scalable access to data st
Physical Intelligence (Pi) is building a general-purpose robotic intelligence system whose core Visual-Language-Action (VLA) model takes visual observations, natural-language instructions, and the...
> which is exactly why we believe memory should live outside of model providers open harness = open memory which everyone should want! The new Anthropic managed agents API is basically the Letta API t