Knowledge catalogue
Claude Opus 4.8 has been made available for use in both Windsurf (Cognition AI's code editor) and Devin CLI (their command-line interface). This release expands access to Anthropic's latest Claude mod
arXiv:2601.00501v2 Announce Type: replace Abstract: We introduce CPPO, a Contrastive Perception Policy Optimization method for finetuning vision--language models (VLMs). Reliable perception is a core
Deploying a Hermes Agent with Fly, Modal, OpenRouter, & Cloudflare 02:43 Managed vs VPS 06:08 Architecture 15:14 Setup 22:23 Deployment 28:00 Access / OIDC 39:57 Hermes and Open WebUI 52:07 Cloudflare
arXiv:2605.28787v1 Announce Type: cross Abstract: In the era of autonomous agents, machine-actionable data is critical for data-driven workflows. For more than a decade, semantic metadata like schema.
arXiv:2605.27935v1 Announce Type: new Abstract: Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this s
arXiv:2605.27566v1 Announce Type: new Abstract: Progress in neural combinatorial optimization for Dynamic Flexible Job Shop Scheduling Problem (DFJSP) is currently hindered by a methodological tension
arXiv:2605.27428v1 Announce Type: new Abstract: Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time
arXiv:2605.28272v1 Announce Type: new Abstract: Real-time synthesis of high-fidelity 3D character motion from audio is a pivotal component for next-generation interactive avatars and virtual assistant
arXiv:2605.27610v1 Announce Type: cross Abstract: The rapid growth of scientific publishing has made it increasingly difficult to track how fast-moving areas evolve. Search engines and LLM-based assis
Evals shape agent behavior. Every eval is a vector that shifts the behavior of your agentic system. More evals ≠ better agents. Instead, build targeted evals that reflect desired behaviors in producti
Google created MapReduce more than 20 years ago to solve the scaling problems in data processing that the then young company was running into. The AI era that we are in now demands efficient, large-sc
arXiv:2605.28751v1 Announce Type: cross Abstract: Linear interpolation between fine-tuned checkpoints has been shown to trace the Pareto front between competing objectives, but whether extrapolative w
Federal prosecutors charged a Google software engineer with making roughly $1.2 million in profits from bets on the prediction market platform Polymarket by using confidential insider information he l
arXiv:2605.27590v1 Announce Type: new Abstract: Remote sensing question answering (RS-QA) often requires more than direct semantic prediction, especially in large-scale forest scenes where ecological
arXiv:2605.28359v1 Announce Type: new Abstract: Evaluating whether large language model (LLM) agents can profit in capital markets is increasingly framed as end-to-end trading: place an agent in a his
Good value for money We gave Grok Build 0.1 one prompt: build a webhook delivery service in TypeScript, Bun, and SQLite. It planned it, built it, and shipped a working demo. Total cost: $1.65. Zero to
Endava, a software services company, leverages OpenAI's Codex to transform its organizational operations into an agentic model where AI agents autonomously handle tasks and decision-making. The approa
Ethan Mollick discusses companies that rapidly depleted their annual token budgets within months, with some spending hundreds of millions of dollars on internal employee use of large language models.
I'm proud to share that @Glean has surpassed 300M ARR, just five months after crossing 200M and growing ~3x over the past 15 months. This is an exciting milestone for Glean, and it's a signal about wh
arXiv:2605.28327v1 Announce Type: cross Abstract: Traditional insurance pricing relies on risk-based principles that ensure actuarial fairness and solvency but do not explicitly account for policyhold
arXiv:2605.28649v1 Announce Type: cross Abstract: LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forg
arXiv:2605.28013v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision.
arXiv:2601.16800v3 Announce Type: replace Abstract: Fine-grained opinion analysis of text provides a detailed understanding of expressed sentiments, including the addressed entity. Although this level
arXiv:2605.28162v1 Announce Type: cross Abstract: Logical operations are essential for quantum computation within quantum error-correcting codes. However, discovering their physical realizations is ch
arXiv:2410.12035v2 Announce Type: replace-cross Abstract: Several variational bounds involving importance weighting ideas generalize the Evidence Lower BOund (ELBO) for marginal likelihood optimizatio
Local Reachy Mini conversations wireless looks like magic! You can bring your friend around the house and get WOW effect from anyone! 🔥 Thanks @andimarafioti for the blog post on how to set this up: h
arXiv:2605.27400v1 Announce Type: cross Abstract: The rapid uptake of generative artificial intelligence (AI) in higher education is reshaping assessment practices and intensifying concerns around aca
models being conscious would be harmful for humanity. it would encroach on our status and dignity. it would limit the type of things we can do with them and use them for. it would vastly accelerate hu
arXiv:2605.28321v1 Announce Type: cross Abstract: As REST APIs become an increasingly significant part of software systems, their validation is becoming more critical. Hence, testing and uncovering un
arXiv:2605.27563v1 Announce Type: cross Abstract: This short note presents a dimension-independent subgaussian concentration bound for Gaussian vectors under coordinate-wise nonlinear mappings. Discov
Rashi Shrivastava / Forbes: Pittsburgh-based Gray Swan, which stress-tests AI models for top frontier AI labs, raised a 40M Series A at a 200M valuation co-led by Wing VC and Madrona — Gray Swan works
arXiv:2605.28201v1 Announce Type: new Abstract: Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into ext
arXiv:2605.27765v1 Announce Type: cross Abstract: Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinforcement learning with large language models by lev
arXiv:2605.27709v1 Announce Type: new Abstract: Mathematical reasoning benchmarks are vital for evaluating large language models (LLMs), but many are static and repeatedly exposed through public evalu
arXiv:2605.28100v1 Announce Type: cross Abstract: In an era where climate change aggravates environmental uncertainties, the identification and detection of event precursors are becoming crucial to mi
arXiv:2605.28154v1 Announce Type: cross Abstract: Programming social robots is challenging for novice robot programmers due to required expertise in planning, interaction design, and programming. Whil
Mistral AI has released Mistral Vibe, an AI agent designed for long-horizon productivity and coding tasks, featuring Work mode, Code mode, a CLI, and additional capabilities. The product consolidates
slide from The Redpoint InfraRed 100 is now live. These are the companies building the infrastructure that powers everything happening in AI right now, from world models and agent runtimes to the sand
arXiv:2505.18647v3 Announce Type: replace-cross Abstract: Simulating trajectories of dynamical systems is a fundamental problem in a wide range of fields such as molecular dynamics, biochemistry, and
arXiv:2605.28779v1 Announce Type: new Abstract: Vision-language models (VLMs) generate fluent causal explanations, but current evaluations cannot distinguish linguistic plausibility from faithful caus
Today, we're releasing LFM2.5-8B-A1B, a device-optimized model designed to power real-life applications on phones, laptops, PCs, robots, and fast & lightweight server-side use-cases. > 8B MoE, 1.5B ac
arXiv:2605.27879v1 Announce Type: new Abstract: Explainable AI (XAI) helps users interpret model behavior and identify potential faults. Agentic XAI systems use Large Language Models (LLMs) to make ex
arXiv:2404.06106v3 Announce Type: replace Abstract: Low dimensional structures appear ubiquitously in the eigenspectra of deep learning matrices in classification networks trained in the overparameter
arXiv:2605.28683v1 Announce Type: new Abstract: Existing benchmarks have laid the foundation for travel planning agents by establishing API-centric paradigms. However, as the capabilities of Autonomou
arXiv:2605.28626v1 Announce Type: new Abstract: Hybrid interpretable models combine a transparent component with a black-box model by assigning some examples to the former and deferring the rest to th
Writer Inc., an enterprise artificial intelligence agent platform used by leading enterprise brands to deliver their voice, today announced new infrastructure aimed at enforcing style, terminology and
arXiv:2602.15919v2 Announce Type: replace-cross Abstract: Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted appro
Been using Grok Build these past few days, and the thing that really got me hooked is Imagine and Imagine Video. I built a full dinosaur encyclopedia site — every image, every video clip on it, all ge
arXiv:2605.27131v1 Announce Type: cross Abstract: Enterprise data platforms face an enduring tension between domain self-service and holistic governance. The data mesh paradigm proposed decentralized
arXiv:2605.27020v1 Announce Type: cross Abstract: The rapid advancement of diffusion-based image generation models has raised serious concerns regarding potential copyright and privacy infringements i
arXiv:2502.03946v5 Announce Type: replace Abstract: Data preprocessing is often paid little attention in machine learning, despite its potentially significant impact on model performance. While automa
Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production-ready because LangSmith Engine turns evaluation from a manu
arXiv:2605.26262v1 Announce Type: new Abstract: Museums are important sites for the dissemination of culture and art. They are institutions rooted in history and tradition; their exhibitions are often
arXiv:2605.27332v1 Announce Type: cross Abstract: Flowcharts are widely used in industrial requirements, but usually remain embedded as static images. Vision Language Models (VLMs) show promise in the
arXiv:2605.27240v1 Announce Type: new Abstract: Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to us
arXiv:2605.26589v1 Announce Type: cross Abstract: Childhood anemia affects around 40% of children aged 6-59 months globally and arises from heterogeneous factors, limiting model generalizability. We e
arXiv:2605.27284v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are increasingly expected to not only complete robot tasks, but also follow human instructions about how those tas
arXiv:2604.04948v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems depend critically on the quality of document preprocessing, yet no prior study has evaluated PDF
arXiv:2605.26620v1 Announce Type: new Abstract: Natural language conveys information at varying levels of granularity, from fine-grained references to broad descriptions. While granularity is fundamen
Nous Research introduced a one-click installation feature in Hermes Agent that allows users to easily install Model Context Protocol (MCP) servers from a curated catalog of Nous-approved integrations.