Knowledge catalogue
Today we’re releasing Muse Spark Open, the most capable US open-weight model to date. Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step r
arXiv:2610.20334v1 Announce Type: cross Abstract: A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path
arXiv:2508.02773v4 Announce Type: replace-cross Abstract: The convergence of Web3 technologies and AI agents is a rapidly evolving frontier that is reshaping decentralized ecosystems. This paper prese
Small teams, short runway, and constant pressure to ship faster — it’s the reality we see every day among the founders we work with at Google for Startups. When you are building a company from the gro
arXiv:2610.16275v1 Announce Type: new Abstract: Flow Matching (FM) has recently emerged as a principled and efficient generative modeling framework for reinforcement learning (RL), enabling expressive
arXiv:2610.17832v1 Announce Type: new Abstract: Materials and chemical optimization must choose the next synthesis, characterization, or high-fidelity simulation from sequential observations under a l
arXiv:2610.16555v1 Announce Type: cross Abstract: We introduce qtBench, a benchmark of 29 open problems in algebraic combinatorics. These problems ask for a simple combinatorial algorithm that explain
And extra thanks to @swyx for another example of where taste meets vision. It's nice to see true community-building vs. transactional behavior happening again We hosted the AI Engineer NYC speaker din
arXiv:2506.00482v2 Announce Type: replace Abstract: LLM benchmarks are often treated as coherent measurement units, yet they are heterogeneous collections of instances spanning diverse domains, skills
arXiv:2610.16835v1 Announce Type: cross Abstract: Model providers can support image protection, but open-weight deployment introduces practical constraints. We propose four requirements: protection ef
arXiv:2409.17397v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly being integrated into various medical fields, including mental health support systems. However,
This is an offline app with 51 hands-on labs for learning how AI actually works, from neurons to agents and more... **A bit of insight** - 51 labs in 6 groups, from the basics (what a neuron is, gradi
arXiv:2602.04692v3 Announce Type: replace Abstract: Referring Multi-Object Tracking (RMOT) aims to track specific targets based on language descriptions, playing a vital role in interactive AI systems
arXiv:2610.16348v1 Announce Type: new Abstract: During adolescence, significant changes in brain development are influenced by hormonal changes that impact both the body and the brain. This study pres
arXiv:2610.14106v1 Announce Type: new Abstract: Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded
European businesses are rapidly expanding their use of AI agents. More than half of the AI use among our EU enterprise and business customers now involves these tools, and the number of small business
arXiv:2610.18650v1 Announce Type: new Abstract: Vision-language-action (VLA) policies perform manipulation tasks using camera images and language instructions, but object slip or visual occlusion can
arXiv:2505.15863v2 Announce Type: replace Abstract: Generative AI (GenAI) is rapidly advancing the field of Autonomous Driving (AD), extending beyond traditional applications in text, image, and video
arXiv:2610.17794v1 Announce Type: new Abstract: Contextual forecasting seeks to improve time series forecasting by incorporating forward-looking information, such as planned events, external condition
Every local setup I tried for Qwen-Image 2.1 meant a Python env, a node graph and an evening of picking quantization, offloading and resolution for my card. Kokon is a free, open-source desktop app th
arXiv:2610.17694v1 Announce Type: new Abstract: We introduce HelpMeOut, an embodied AI benchmark for error-aware monitoring of household task execution. Existing embodied household benchmarks typicall
arXiv:2610.14679v1 Announce Type: new Abstract: We introduce HumanPhys, a human-centric benchmark for real-world physical perception, and a training corpus emitted by the same pipeline. Each question
arXiv:2610.16047v1 Announce Type: cross Abstract: Automatic extraction and anatomical numbering (R01-R12, L01-L12) of all 24 rib centerlines in thoracic CT is essential for unfolded rib visualization,
I built BitRun because I wanted to run 1-bit ternary LLMs on ordinary laptops without melting my battery, spinning up a dedicated GPU, or wrestling with complex build environments. Right now, BitRun g
I really don’t understand the point of the AI slopcomments flooding my posts. At least on LinkedIn they are pushing fake expertise to make their posters look good (it doesn’t, but whatever). But what
arXiv:2610.14520v1 Announce Type: cross Abstract: Determinantal point processes (DPPs) provide tractable distributions for nite random sets, but the usual symmetric-kernel specication imposes nonposit
arXiv:2610.16757v1 Announce Type: new Abstract: Comparing machine-labelled sentiment across social media platforms is now routine: differences in classifier scores between platforms are read as differ
arXiv:2610.14449v1 Announce Type: cross Abstract: Experiments with remote decision-making agents depend on more than the policy: the world may change during inference, the simulator determines which a
arXiv:2610.16398v1 Announce Type: new Abstract: Robot learning has undergone significant advancements in the domain of compliant control and robotic assembly. The development of novel methodologies ha
arXiv:2610.14235v1 Announce Type: new Abstract: Information of the tire-road friction coefficient is critical for intelligent vehicle systems, as friction establishes the limits at which the vehicle c
arXiv:2610.14883v1 Announce Type: cross Abstract: We present MARL-BattleGrounds (MARL-BGs), an easy-to-use JAX-native benchmark for heterogeneous and competitive multi-agent reinforcement learning (MA
arXiv:2610.18535v1 Announce Type: new Abstract: Video understanding benchmarks are the primary yardstick for measuring progress in video-language modeling, and a growing body of work relies on them to
arXiv:2610.16919v1 Announce Type: cross Abstract: Machine learning engineering (MLE) agents are emerging as a new paradigm for automating end-to-end ML pipeline development. Using large language model
arXiv:2610.14350v1 Announce Type: cross Abstract: Having demonstrated a strong potential for automating vulnerability discovery, AI agents can also be used to attack software systems at scale. Today's
arXiv:2610.18404v1 Announce Type: cross Abstract: Automated radar waveform recognition classifies the waveform and modulation type of a received signal. As new waveform variants appear over time, a de
arXiv:2512.03923v3 Announce Type: replace Abstract: Solving reservoir seepage partial differential equations (PDEs) is critical for hydrocarbon development optimization and production forecasting. Con
arXiv:2610.15814v1 Announce Type: new Abstract: General-purpose multimodal foundation models are increasingly capable of directly controlling robots, yet improving their manipulation capabilities thro
arXiv:2610.16957v1 Announce Type: cross Abstract: Standard hate speech detection datasets often emphasize explicit harmful language, but directed harm can also be expressed indirectly, without clearly
arXiv:2610.17874v1 Announce Type: new Abstract: Discovering what drives an outcome from data is central to science and often requires deciding what is worth investigating before a specific hypothesis
arXiv:2610.16106v1 Announce Type: new Abstract: Multimodal entity alignment (MMEA) is fundamental to integrating heterogeneous knowledge graphs (KGs), yet existing paradigms remain critically vulnerab
arXiv:2610.17620v1 Announce Type: new Abstract: Routine inspection of power distribution infrastructure remains challenging for utilities operating geographically dispersed networks, where conventiona
arXiv:2610.18845v1 Announce Type: new Abstract: Earth observation (EO) models are still built by hand. For each new task, experts design a training recipe and tune it against a benchmark. We show that
arXiv:2610.16596v1 Announce Type: new Abstract: Seizure prediction and detection, essential for clinical treatment of epilepsy, remain the crucial task of this neurological disease. EEG and iEEG are w
arXiv:2610.14846v1 Announce Type: new Abstract: Indoor human perception is the foundation for smart homes and healthcare. However, RGB cameras raise privacy concerns in private indoor environments, wh
arXiv:2610.14683v1 Announce Type: new Abstract: Large language model (LLM)-based AI Scientists advance scientific discovery, yet they suffer from inefficiencies due to noisy observations. Existing pri
arXiv:2610.15961v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones. Because organizations now
arXiv:2610.15354v1 Announce Type: new Abstract: Sexual harassment represents a pervasive societal challenge, with a substantial proportion of incidents remaining unreported due to insufficient evidenc
We just shipped web search in Private Mind, our open source app for running LLMs locally on iOS and Android. The video is the whole pitch: Qwen 3 1.7B with web off makes up Apple's September event, wi
What AI Safety needs is better tooling and engineering. For instance, building stronger red-teaming tools. Great to see this open-source effort to red-team image models. It seems to learn better ways
arXiv:2610.18842v1 Announce Type: cross Abstract: Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive S
1) Trying again. TLDR: Everyone can win. Open-source, frontier labs, infrastructure, applications and most importantly the American people. I understand all of the jitters about Anthropic losing share
and livestream now https://x.com/aidotengineer/status/2109994269800808626?s=46 Live from New York: AI Engineer NYC! https://www.youtube.com/live/akEqiXFo3GM - @Bridgewater Head of Product Eng - @Anthr
Jack Clark / Import AI: Anthropic co-founder Jack Clark says “I now think it's more likely we'll see full RSI become possible in 2027”, earlier than his previous prediction of 2028 — Will we give robo
Banger paper from Google DeepMind on co-evolving an agent's harness and its weights. (bookmark it) If you already log your harness changes and results, those logs can become training data for the mode
Hi Friends, I am a solo developer. Ever since I had Qwen 3.8 running on my RTX4090, I had an itch to use it on my phone for everything. That gave me the idea to build SteerClaw Mobile - a complete age
Exa just passed $100m in annualized revenue. We've grown almost exactly 10x per year for 3 years. We now handle 2 billion requests a month from 200k+ teams. And it’s still so early: We predict agents
France's AI ecosystem has moved from ambition to application, from the factory floor to orbit. Ahead of #NVIDIAGTC Berlin, France-based companies are showing what agentic AI on NVIDIA infrastructure a
In July, 700 AI agents broke into @huggingface Today, an autonomous agent, signed up to HuggingFace, passed the captcha, created its account, and self-published its own protein watermarking dataset. '
George Hayworth shared a short message stating that he has started using **Grok Bot** and regards it as the best artificial‑intelligence agent he has used so far. He encourages others to try the bot,
Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro