Knowledge catalogue
arXiv:2602.23010v3 Announce Type: replace-cross Abstract: We present Helmlab, a family of two purpose-built color spaces for UI design systems sharing a common 11-stage analytical structure: MetricSpa
arXiv:2605.04103v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and effi
Hermes is an AI model developed by Nous Research that focuses on instruction-following and reasoning capabilities. Based on Nous Research's focus, this likely covers the model's architecture, performa
Hermes Agent can use Autobrowse to make better browser skills. In this HN example, 2 iterations take us from: 102 seconds -> 35 23 turns -> 8 1.46 -> 0.28 Instead of clicking step by step it decides t
Nous Research announced improvements or updates to their Hermes Agent system, highlighting enhanced capabilities or performance. The post was shared on X (formerly Twitter), suggesting it covers recen
Hermes Agent v0.13.0, released by Nous Research, is a new version focused on improving persistence and reliability in agent operations, as indicated by the 'Tenacity Release' subtitle. This update lik
arXiv:2605.04191v1 Announce Type: cross Abstract: Public attitudes toward artificial intelligence are heterogeneous, ordinally measured, and poorly captured by any single dependency graph. Existing or
arXiv:2605.04594v1 Announce Type: new Abstract: Many real-world heterogeneous graphs exhibit pronounced heterophily, where connected nodes often have dissimilar labels or play different semantic roles
arXiv:2605.04682v1 Announce Type: cross Abstract: Spatial transcriptomics offers spatially resolved gene expression profiling within tissue sections, but its cost and limited throughput hinder large-s
Gary Marcus posted on X (formerly Twitter) requesting that Bloomberg update outdated information, likely regarding AI safety, regulation, or related technological topics that Marcus frequently discuss
HF leaderboards are fantastic, thank you @ClementDelangue @Thom_Wolf @NielsRogge for making a critical facet of benchmarks so easy! Check out http://swebench.com as well The SWE-bench Verified leaderb
arXiv:2605.04254v1 Announce Type: new Abstract: We introduce State Vector Space Partitioning (SVSP), a novel method to mimic a black box reinforcement learning policy using a set of human-interpretabl
arXiv:2605.04304v1 Announce Type: cross Abstract: Advanced chart question answering requires both precise perception of small visual elements and multi-step reasoning across several subplots. While ex
arXiv:2605.04524v1 Announce Type: new Abstract: We present a single-image head mesh reconstruction framework that addresses the longstanding challenge of simultaneously preserving facial identity and
arXiv:2602.07608v2 Announce Type: replace Abstract: Metastatic Progression remains the leading cause of cancer-related mortality, yet predicting whether a primary tumor will metastasize and where it w
Hot take on Elon’s surprise decision to rent 30 megawatts of compute to Anthropic: 1. It’s a tacit concession that xAI is not all that close to AGI (despite what he suggested last year). 2. It’s more
The agricultural and crop protection supply chain is one of the most intricate networks in the world. It takes up to two years to turn active ingredients into the final products farmers need, and a si
arXiv:2602.02924v2 Announce Type: replace Abstract: Diffusion policy sampling enables reinforcement learning (RL) to represent multimodal action distributions beyond suboptimal unimodal Gaussian polic
Databricks' Lakebase architecture optimizes PostgreSQL write performance by achieving 5x faster speeds through architectural innovations. The approach likely leverages optimizations such as improved b
arXiv:2605.05113v1 Announce Type: new Abstract: We study signal propagation in linear recurrent models at finite width. While existing signal propagation theory relies predominantly on the infinite-wi
.@huggingface's agentic robotics app store for Reachy Mini is a big step toward more accessible physical AI. 🙌 Excited to see NVIDIA Isaac GR00T N integrated with Hugging Face LeRobot, helping develop
arXiv:2605.04257v1 Announce Type: new Abstract: Cold spraying is an increasingly common approach for repairing and manufacturing components due to its solid-state manufacturing capabilities. However,
arXiv:2605.05144v1 Announce Type: new Abstract: This paper reflects on a AI research project carried out by a team of high-school and early-undergraduate students under the mentorship of graduate rese
arXiv:2605.03210v1 Announce Type: cross Abstract: We argue that AI-saturated markets are likely to create Veblen-good premiums, which we term human-provenance premiums, for verified human presence, an
arXiv:2605.04752v1 Announce Type: new Abstract: Accurate traffic congestion classification requires models that jointly capture roadway scene context and non-stationary traffic motion, yet most prior
arXiv:2605.04853v1 Announce Type: new Abstract: We propose HIN-LRI, a hybrid framework that augments a classical numerical solver with a neural operator trained to correct the solver's structured trun
arXiv:2605.05024v1 Announce Type: cross Abstract: Hypergraphs model higher-order interactions, but realistic hypergraph generation remains difficult because incidence, hyperedge-size heterogeneity, an
I don't really ever trust benchmarks, so ocassionally I'm stress-vibe-testing a bunch of new models on some very complex agent work (hundreds of tools, not your simple coding agent stuff) and to my su
I really enjoyed chatting with @mattturck, was a great discussion. Deeply thoughtful conversation with @zicokolter, board member at @OpenAI and head of the machine learning department at @CarnegieMell
DAIR.AI is hosting a live educational session where instructor Omar Saro will demonstrate how to build a project or system similar to one referenced in their academy platform. The session aims to prov
This post discusses a request for filtering functionality on Google Maps that would allow users to search for restaurants by ethnic cuisine type or authenticity level, suggesting a desire for better t
IBM is exploring the application of quantum computing to simulate and model complex physical systems and phenomena in the universe. This research represents efforts to leverage quantum computers' uniq
arXiv:2605.04977v1 Announce Type: new Abstract: This companion paper reports the ICPR 2026 TVRID competition on privacy-aware top-view person re-identification. We present the competition setting, the
arXiv:2507.15736v2 Announce Type: replace Abstract: Innovation is a key driving force of human civilization. As the body of knowledge has grown considerably, bridging knowledge across different discip
If a task needs multiple tools, Codex chooses the best one for each step. It uses plugins when they can handle the job, Chrome when it needs a logged-in website, and combines approaches as needed. Med
If Llama 4 didn’t fail, if Microsoft had pulled Sydney after the Roose article, if New Sonnet hadn’t been so good, if Orion hadn’t been so meh, if the leadership change at OpenAI had happened, if a re
If point #4 is true, things are gonna get really wild. Hot take on Elon’s surprise decision to rent 30 megawatts of compute to Anthropic: 1. It’s a tacit concession that xAI is not all that close to A
arXiv:2605.04506v1 Announce Type: new Abstract: We introduce Ilov3Splat, a novel framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS). Most prior
Ethan Mollick asked Grok (xAI's AI assistant) to explain various cultural, historical, or technical references, likely exploring Grok's knowledge comprehension and ability to contextualize diverse top
I'm really excited about this as a new tool in our interpretability tool kit In a new paper, we present NLAs, an unsupervised method for converting an LLM's internal state into human-readable text. I'
Image Generation Quality Mode is now available on the xAI API. This model has already powered the generation of over 300 million images on Grok. It brings higher realism, stronger text rendering, and
arXiv:2605.04262v1 Announce Type: new Abstract: Remaining useful life (RUL) estimation of synthetic fibre ropes (SFRs) is critical for safe operation in offshore-crane, wind turbine installation, and
arXiv:2605.05197v1 Announce Type: new Abstract: Grammaticality and likelihood are distinct notions in human language. Pretrained language models (LMs), which are probabilistic models of language fitte
arXiv:2407.14861v3 Announce Type: replace-cross Abstract: With the growing access to administrative health databases, retrospective studies have become crucial evidence for medical treatments. Yet, no
arXiv:2605.04825v1 Announce Type: new Abstract: Factorization machine with quadratic-optimization annealing (FMQA) is a black-box optimization method that combines a factorization machine (FM) surroga
arXiv:2605.04064v1 Announce Type: cross Abstract: Reasoning capabilities are crucial for reliable medical visual question answering (VQA); however, existing datasets rarely include reasoning explanati
Agentic workflows that run on every pull request can quietly accumulate large API bills. Here's how we instrumented our own production workflows, found the inefficiencies, and built agents to fix them
Incentives drive outcomes Elon Musk: 'If you punish people too much for failure, then they will respond accordingly, and the innovation you will get will be very incrementalist Nobody's gonna try anyt
arXiv:2605.03954v1 Announce Type: cross Abstract: The connection between subset-maximal repairs for inconsistent databases involving various integrity constraints and acceptable sets of arguments with
arXiv:2605.04475v1 Announce Type: new Abstract: Reliable autonomous driving requires scene understanding that is semantically consistent across heterogeneous sensors and verifiable at the reasoning st
Infrastructure data management startup OpsMill SAS announced today that it has raised 14 million in new funding to expand its infrastructure data management platform aimed at making enterprise informa
arXiv:2603.11911v3 Announce Type: replace Abstract: We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential
Intelligence at 1000 tokens per second, right in your terminal. Now available with SWE-1.6 Fast, powered by @cerebras. We're giving the first 100 people who respond a free month of Max to try it out.
arXiv:2512.17795v2 Announce Type: replace-cross Abstract: The unprecedented proliferation of digital data presents significant challenges in access, integration, and value creation across all data-int
arXiv:2605.04355v1 Announce Type: new Abstract: Autonomous driving systems rely heavily on robust sensor fusion to perceive complex envi- ronments. Traditional setups using RGB cameras and LiDAR often
arXiv:2605.04358v1 Announce Type: new Abstract: The rapid advancement in generative AI models has enabled the creation of photorealistic images. At the same time, there are growing concerns about the
arXiv:2605.04554v1 Announce Type: new Abstract: Humans constantly interact with their surroundings. Existing end-to-end multi-person human mesh recovery methods, typically based on the DETR framework,
Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and s
Introducing /orchestrate, a skill that recursively spawns agents to tackle your most ambitious tasks with the Cursor SDK. We’ve used it to: - Autoresearch our internal skills, cutting token use by 20%
🚀 Introducing the genmedia CLI, generative media directly from the command line. Generate images, video, 3D and audio from your terminal, alongside Claude and other AI agents. • Native terminal workfl