Knowledge catalogue
Another brilliant paper from Meta. This one is worth reading if you work on production-grade ranking or recommendation systems. Meta deployed an autonomous agent that runs the ML iteration cycle acros
arXiv:2609.05776v1 Announce Type: new Abstract: Evaluating enterprise agents on domain-specific benchmarks is critical, yet public benchmarks rarely evaluate whether agents can integrate business know
arXiv:2609.05576v1 Announce Type: new Abstract: The paradigm of LLMs has rapidly shifted from passive language interfaces to autonomous Claw-like agents that execute long-horizon tasks across stateful
so i saw that openui.com released OUI-1, a model fine-tuned on DiffusionGemma. the training dataset uses OpenUI-Lang, a custom DSL (domain-specific language), instead of plain HTML, Markdown, or React
In v0.10 we achieved significant speedups over v0.9. The video shows the maximum speedups we measured for specific groups of models. Among LLMs, the biggest gain came from Qwen3 0.6B, which runs over
arXiv:2609.06740v1 Announce Type: new Abstract: Smart agriculture platforms usually bundle AI diagnosis, IoT sensing and decision push into a single package, so the green benefit attributable to each
arXiv:2609.06128v1 Announce Type: new Abstract: Production LLM agents execute tool-calling loops, retrieval chains, and compositional workflows in multiple modes, yet execution semantics are often cou
arXiv:2609.05749v1 Announce Type: new Abstract: Work on the risks of artificial intelligence has focused predominantly on capability risk: the danger that systems become too powerful, too autonomous,
arXiv:2609.09372v1 Announce Type: cross Abstract: Although MMLU is widely adopted as a benchmark for calibrating general AI capabilities, we psychometrically demonstrate that its aggregate score prima
AI companies like @cohere build on both sides of the token economy: the models and the products that use them. By moving production workloads to NVIDIA Blackwell, Cohere lowered token costs, increased
arXiv:2505.20498v3 Announce Type: replace Abstract: Vision-based tactile sensing is widely used in perception, reconstruction, and robotic manipulation, yet collecting large-scale tactile data remains
arXiv:2507.05134v2 Announce Type: replace Abstract: We present a deep learning approach to extract physical parameters (e.g., mobility, Schottky contact barrier height, defect profiles) of two-dimensi
arXiv:2609.07111v1 Announce Type: new Abstract: Quadruped robot locomotion policies are often trained using reinforcement learning, which in turn relies heavily on hand-crafted reward functions. Desig
We are excited to share that Gartner has named Google a Leader in its inaugural 2026 Magic Quadrant for Enterprise AI Assistants. In this comprehensive evaluation of top enterprise AI assistant vendor
arXiv:2609.08800v1 Announce Type: cross Abstract: Three properties determine whether a differentiable simulator can drive gradient-based optimization through contact: simulation accuracy, gradient rel
Encode‑Prefill‑Decode (EPD) disaggregation is an inference optimization in NVIDIA Dynamo that separates vision encoding from LLM prefill–decode stages for multimodal requests. On image‑heavy prompts,
Hello LocalLLaMA Fam! I built this project because I, like many of us here, enjoy local AI and have a nice setup, but still find myself reaching for Cloud-based AI due to their convenience. My models
Gemma 4 12B runs on an RTX PRO 4500 Blackwell. Gemma 4 E2B run on a Jetson Orin NX 16GB; similar performance is expected on a Jetson Orin Nano Super 8GB. Both systems use a reSpeaker Flex 4-mic array
Tae Kim / Key Context: Astra working with Blender via computer use feels like magic, showing computer use could be the fourth demand wave after chatbots, reasoning, and agentic coding — AI computer to
arXiv:2609.04711v1 Announce Type: cross Abstract: Generative AI and coding agents can accelerate research software development, but they also increase the need for efficient software discovery and mai
arXiv:2606.19667v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves factual grounding, but it also lengthens prompts and raises prefill cost. Prefix caching in serving en
I got 2x 20GB RTX 3080s + 128GB of DDR4 2666hz RAM (only 4 of 6 channels populated) + a Xeon 6148 I've always been a llama.cpp person and I've been running Unsloth's Q4_K_XL quant of Qwen 3.8 Flash Ne
// From Language Models to World-Acting Systems // A critical review of agentic AI, and a framework that is genuinely useful for deciding how much authority to hand an agent. Here is how it works. The
Our research team has been exploring an alternative approach to achieving interactivity and better responsiveness with LLM systems. One of the team members wrote up a post about it: https://research.y
LayerStoRm: GLM-5.3-Flash UD-Q4_K_XL (186 GiB) at 1M context on 2× RTX 5090 + 2× RTX 5080 (96 GB VRAM total) using RAM for the pinned experts. LayerStoRm is a (still experimental) MIT-licensed continu
I keep seeing these massive ultimate chatgpt prompt posts all over social media, like we’re still using Chat and other LLMs the same way we did when they first came out. Meanwhile the more I use AI, t
Right, so this is going to be embarrassing but it's presumably something we've all been through at one point or another, and I guess this is my first time resolving something like this in the way that
As companies entrust more responsibility to artificial intelligence, managing governance and regulatory reporting becomes even more essential. Workiva Inc.’s platform provides AI-powered collaboration
arXiv:2609.03716v1 Announce Type: new Abstract: Data centers are increasingly optimized by artificial intelligence and, at the same time, increasingly loaded by it. The literature treats these as two
arXiv:2609.03721v1 Announce Type: cross Abstract: Context: Architectural Design Decisions (ADDs) capture the rationale behind the structure and evolution of software systems but are rarely documented
arXiv:2609.03594v1 Announce Type: cross Abstract: As integrated circuit technology scales into the nanometer regime, the traditional disconnect between logic synthesis and physical design has led to s
arXiv:2609.03209v1 Announce Type: new Abstract: We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic policy selects and runs a pre-approv
Moving Large Language Models (LLMs) from experimental prototypes into enterprise production exposes a critical truth: your infrastructure dictates both your performance ceilings and your unit economic
arXiv:2609.04159v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale:
arXiv:2606.19264v2 Announce Type: replace-cross Abstract: The knowledge encoded in large language models (LLMs) can serve as a substrate for structured reasoning over variables describing a complex wo
arXiv:2609.03005v1 Announce Type: new Abstract: Many NLP tasks, such as summarization and extractive question answering, reduce to retrieving relevant content from documents under two constraints: cov
arXiv:2609.03920v1 Announce Type: new Abstract: The emergence of agentic AI and LLM-based multi-agent systems (MAS) presents unprecedented opportunities for automating complex tasks, while simultaneou
arXiv:2609.01861v1 Announce Type: new Abstract: The performance of an LLM agent depends on the scaffold around a frozen model. A common way to improve that scaffold is to use a coding agent as an opti
Brilliant paper on long-horizon agents. They cut 78.9% of an agent's LLM calls while raising its success rate. Here is how: It turns out that ReAct issues one primitive action per model round. That al
arXiv:2604.02198v2 Announce Type: replace Abstract: While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as av
arXiv:2609.02106v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly explore many candidate states of relational data in parallel, each of which should remain isolated, rep
For the ninth consecutive year, Gartner® has named Google a Leader in the Gartner Magic Quadrant™ for Strategic Cloud Platform Services, positioned furthest for Completeness of Vision. We believe this
I tested Astra early. What I would want EVERY business professional to know about the brand-new model from OpenAI: 1) Computer use and browser use are just incredible. I'm confident that pretty much a
Maxwell Zeff / Wired: OpenAI calls GPT-6 Astra the “world's best computer use model”; in tests, it booked DMV appointments and searched job listings faster than the average person — OpenAI leaders thi
arXiv:2609.02886v1 Announce Type: new Abstract: We introduce SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference. Training
arXiv:2609.02846v1 Announce Type: new Abstract: Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer E
arXiv:2609.02322v1 Announce Type: cross Abstract: The first problem of modeling the world is not just estimating the right parameters or causal structure, but deciding what should be represented at al
arXiv:2609.00714v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems (MAS) have shown strong potential for solving complex tasks, yet their development forces a tradeof
arXiv:2609.00099v1 Announce Type: new Abstract: Corrosion accounts for approximately 4% of global GDP, and reliable prediction is essential for timely mitigation. Machine learning effectively predicts
arXiv:2609.00546v1 Announce Type: cross Abstract: Agent systems are commonly described by the model and harness that currently produce their behavior. That boundary is useful for one execution but und
arXiv:2608.28592v1 Announce Type: new Abstract: Large language models (LLMs) achieve high scores on medical knowledge examinations, yet real-world oncology is not a knowledge test--it is a sequence of
arXiv:2508.04865v4 Announce Type: replace Abstract: Large language models (LLMs) already excel at writing code in high-resource languages such as Python and JavaScript, yet stumble on low-resource lan
And that's the bottom line. It's the neuro-symbolic aspect of AI that's moved the needle to where things are today. LLMs simply handled the fuzzy natural language aspect that always tripped up the sym
arXiv:2608.29026v1 Announce Type: new Abstract: Deep learning has a powerful capability of feature extraction. However, the lack of fairness and interpretability in deep neural networks poses limitati
Introduction Beginning in 2024 Mandiant investigated a string of compromises affecting Brazilian financial services, retail, and eCommerce organizations. Google Threat Intelligence Group (GTIG) tracks
arXiv:2608.30584v1 Announce Type: new Abstract: Despite the impressive progress of recent MLLMs on spatio-temporal video grounding (STVG), existing evaluations and training data focus primarily on sim
arXiv:2608.29305v1 Announce Type: cross Abstract: Large language model (LLM) agents have demonstrated remarkable proficiency in manually constructed environments, yet their performance frequently coll
arXiv:2608.29420v1 Announce Type: new Abstract: Frontier-model leaderboards now rank systems based on economic benchmarks, tests of how well models carry out professional tasks from software engineeri
arXiv:2509.25256v4 Announce Type: replace-cross Abstract: The systematic assessment of AI systems is increasingly vital as these technologies enter high-stakes domains. To address this, the EU's Artif
arXiv:2608.29197v1 Announce Type: cross Abstract: Decision-time equilibrium search carried poker to superhuman play, but it has so far relied on tractable subgames: a handful of actions per decision,