Knowledge catalogue
ml-intern from @huggingface is such a cool repository, an 🤖 agentic harness that allows you to wield the larger🤗ecosystem to run all the tasks a ml researcher would. it's all one can ask for as a side
ml-intern now notifies you when it needs input! Amazing for those 12h+ autonomous LLM training runs The ML Intern can now ping you on Slack when it's finished training models, generating datasets, or
arXiv:2604.22031v1 Announce Type: cross Abstract: We propose Mochi, a Graph Foundation Model that addresses task unification and training efficiency by adopting a meta-learning based training framewor
Model page: https://ollama.com/library/deepseek-v4-pro Try it with Codex: ollama launch codex --model deepseek-v4-pro:cloud Try it with OpenClaw: ollama launch openclaw --model deepseek-v4-pro:cloud T
arXiv:2604.21989v1 Announce Type: cross Abstract: The problem of controlling hybrid dynamical systems using model predictive control (MPC) is formulated and sufficient conditions for asymptotic stabil
arXiv:2604.21937v1 Announce Type: new Abstract: Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specializ
🗓️ @mondaydotcom is scheduled for Interrupt. Monday Sidekick is an AI assistant that can execute work, manage tasks, and conduct research autonomously. At Interrupt, the Agent Conference by LangChain,
Gerrit De Vynck / Washington Post: More than 600 Google employees, including many from DeepMind, sign a letter to Sundar Pichai demanding he bar the DOD from using Google's AI for classified work — “W
arXiv:2509.22166v4 Announce Type: replace-cross Abstract: The demand for efficient large language model (LLM) inference has intensified the focus on sparsification techniques. While semi-structured (N
arXiv:2604.22492v1 Announce Type: cross Abstract: Understanding social dominance in animal behavior is critical for neuroscience and behavioral studies. In this work, we explore the capability of Mult
arXiv:2604.22548v1 Announce Type: cross Abstract: Problem definition: Data-driven models in machine learning have enabled efficient management of production systems. However, a majority of machine lea
arXiv:2604.21991v1 Announce Type: cross Abstract: Multi-task optimization is a powerful approach for solving a large number of tasks in parallel. However, existing algorithms face distinct limitations
arXiv:2602.06019v2 Announce Type: replace Abstract: Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and buildi
arXiv:2604.22212v1 Announce Type: cross Abstract: In spite of the utility of 3-D electron back-scattered diffraction (EBSD) microscopy, the data collection process can be time-consuming with serial-se
arXiv:2510.03248v3 Announce Type: replace-cross Abstract: Background: Traumatic brain injury modeling requires integrating volumetric neuroimaging, demographic parameters, and acquisition metadata. Fi
arXiv:2410.21548v3 Announce Type: replace Abstract: Large language models have drastically changed the prospects of AI by introducing technologies for more complex natural language processing. However
All 22 members of the National Science Board, which advises and oversees the US National Science Foundation, were fired on April 24 without explanation. Members received no explanation for their termi
arXiv:2604.22239v1 Announce Type: cross Abstract: This paper introduces the task of analytical question answering over large, semi-structured document collections. We present MuDABench, a benchmark fo
arXiv:2408.16286v5 Announce Type: replace Abstract: Designing a safe policy for uncertain environments is crucial in real-world control systems. However, this challenge remains inadequately addressed
arXiv:2604.22158v1 Announce Type: cross Abstract: We study the problem of adaptive control of the stochastic linear quadratic regulator (LQR) with constraints that must be satisfied at every time step
arXiv:2604.22730v1 Announce Type: cross Abstract: We investigate whether neural models trained exclusively on modern morphological data can recover cross-lingual lexical structure consistent with hist
arXiv:2510.25977v4 Announce Type: replace Abstract: Emerging AI accelerators have started to gain attention and offer new opportunities for efficient inference of large language models (LLMs). Trainiu
New work with @AlecRad and @DavidDuvenaud: Have you ever dreamed of talking to someone from the past? Introducing talkie, a 13B model trained only on pre-1931 text. Vintage models should help us to un
🚨 NEWS: Emirates upgrades its iconic A380 with Starlink high-speed Wi-Fi, delivering “better-than-home” internet at 40,000 feet. • Up to 3 Starlink antennas on each A380 for massive speed boost • Inte
Scientists are concerned about the upcoming El Niño because it's developing against the backdrop of already-elevated global temperatures from climate change, which could create a 'perfect storm' of cl
arXiv:2511.07003v2 Announce Type: replace Abstract: Large language models have significantly advanced Multilingual Machine Translation (MMT), yet scaling to many languages while keeping quality robust
arXiv:2604.22518v1 Announce Type: new Abstract: We introduce NONSAC (Non-Minimal Sampling and Consensus), a general framework for robust and scalable model estimation from arbitrarily large datasets c
arXiv:2604.22439v1 Announce Type: new Abstract: We propose a neural regularization method that refines the noisy 3D semantic field produced by lifting multi-view inconsistent 2D features, in order to
arXiv:2509.20886v2 Announce Type: replace Abstract: Video sequences often contain structured noise and background artifacts that obscure dynamic content, posing challenges for accurate analysis and re
arXiv:2604.22005v1 Announce Type: cross Abstract: Accurate yet low-latency channel state information (CSI) acquisition is essential for multiple-input multiple-output (MIMO) communication systems. Whi
arXiv:2604.22240v1 Announce Type: new Abstract: Generative world models increasingly rely on 4D occupancy for realistic autonomous driving simulation. However, existing generation frameworks depend on
arXiv:2601.13895v2 Announce Type: replace-cross Abstract: Change Detection (CD) is a fundamental task in remote sensing. It monitors the evolution of land cover over time. Based on this, Open-Vocabula
arXiv:2604.22230v1 Announce Type: cross Abstract: Benchmark hacking refers to tuning a machine learning model to score highly on certain evaluation criteria without improving true generalization or fa
arXiv:2501.19277v4 Announce Type: replace-cross Abstract: We study online assortment optimization under stochastic choice when a decision maker simultaneously values cumulative revenue performance and
On Star Price's new @hitpausepod podcast, ControlAI's US Director Connor Leahy (@NPCollapse) explains how AIs can already tell when they're being tested. Currently, we can still catch them cheating, b
arXiv:2604.22455v1 Announce Type: new Abstract: A core component of any AI-Augmented Business Process Management System (ABPMS) is the process frame, which gives the system process-awareness and defin
arXiv:2604.22540v1 Announce Type: cross Abstract: Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit
arXiv:2604.22354v1 Announce Type: new Abstract: Each scanner possesses its unique characteristics and exhibits its distinct sampling error distribution. Training a network on a dataset that includes d
arXiv:2407.08750v4 Announce Type: replace-cross Abstract: Large-scale streaming data are common in modern machine learning applications and have led to the development of online learning algorithms. M
Open models. National scale. Real scientific impact. Read more: https://www.prnewswire.com/news-releases/together-ai-joins-us-department-of-energys-genesis-mission-to-accelerate-american-scientific-di
A widely-downloaded open source package called element-data was compromised after attackers exploited a vulnerability in developer account workflows, gaining access to signing keys and releasing a mal
OpenAI Group PBC and Microsoft Corp. have revised several sections of the contract that governs their technology partnership. The update, which was announced today, is at least the third that the comp
OpenAI has achieved FedRAMP Moderate authorization, enabling U.S. federal agencies to use OpenAI's services while meeting federal security and compliance requirements. This certification demonstrates
OpenAi bait-and-switched Elon, pretending to a non-profit mission to save humanity until it pocketed his donations. Elon should win. BREAKING: Elon Musk and OpenAI trial officially set to begin today
Microsoft will continue to have a license to OpenAI IP through 2032, but Microsoft's license is now non-exclusive, allowing OpenAI to serve its products across any cloud provider . Microsoft will stop
🚨 OpenAI just REMOVED the AGI clause that was a structural protection of OpenAI's charitable mission, while jury selection was happening today The 2019 capped-profit structure had three protections fo
arXiv:2604.22676v1 Announce Type: new Abstract: Graph neural networks achieve strong node-classification accuracy, but their learned message passing entangles ego attributes, neighborhood smoothing, h
arXiv:2601.05245v2 Announce Type: replace Abstract: We prove tight lower bounds for online multicalibration, establishing an information-theoretic separation from marginal calibration. In the general
arXiv:2604.22067v1 Announce Type: cross Abstract: Psychiatric intake is a sequential, high-stakes information-gathering process in which clinicians must decide what to ask, in what order, and how to i
arXiv:2604.22168v1 Announce Type: new Abstract: Here, we explore the problem of error propagation mitigation in modular digital twins as a sequential decision process. Building on a companion study th
arXiv:2510.18999v2 Announce Type: replace-cross Abstract: Reconstructing signed distance functions (SDFs) from point cloud data benefits many robot autonomy capabilities, including localization, mappi
Ornstein-Hermes-27B-MLX live https://huggingface.co/GestaltLabs/Ornstein-Hermes-3.6-27b-MLX-16bit https://huggingface.co/GestaltLabs/Ornstein-Hermes-3.6-27b-MLX-8bit https://huggingface.co/GestaltLabs
arXiv:2604.22074v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) on chain-of-thought reasoning has become a standard part of language model post-training recipes.
arXiv:2604.22386v1 Announce Type: cross Abstract: One of the major limits of kernel ridge regression (KRR) is that storing and manipulating the kernel matrix K_n for n samples requires O(n^2) space, w
arXiv:2604.22129v1 Announce Type: new Abstract: Gaussian Splatting (GS) has emerged as an efficient approach for high-quality novel view synthesis. While early GS variants struggled to accurately mode
arXiv:2511.05456v2 Announce Type: replace Abstract: Graph network-based simulators (GNS) have demonstrated strong potential for learning particle-based physics (such as fluids, deformable solids, and
ParseBench: A benchmark for document parsing agents @llama_index just shipped a benchmark with 2k verified pages for real enterprise documents. Benchmarks are the major underrated component in the ML
Ineffable Intelligence is building a superlearner—an AI system that discovers knowledge through its own experience rather than human data, using reinforcement learning without pre-training. The compan
arXiv:2604.22658v1 Announce Type: new Abstract: Single-view 3D shape retrieval is a fundamental yet challenging task that is increasingly important with the growth of available 3D data. Existing appro
Pay attention to this one, AI devs. If you're building multi-agent systems, you're probably wiring static org charts. New research argues they should look more like a labor market. The paper introduce