Knowledge catalogue
Introducing VultronRetriever, a family of open visual document retrieval models built on Vultr. Achieve state-of-the-art retrieval performance with smaller indexes, higher throughput, and support for
A comprehensive evaluation of over 30 frontier embodied AI models reveals that current generalist robot policies lack the robustness needed for reliable real-world manipulation tasks. The analysis dem
arXiv:2607.06630v1 Announce Type: new Abstract: Formal robustness certificates for embedded neural-interface models can pass while task accuracy collapses: at perturbation budget e=0.25, EEGNet classi
arXiv:2607.06120v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploi
arXiv:2607.06553v1 Announce Type: new Abstract: Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and
Happy to announce that we’ve enlisted @FireworksAI_HQ as our primary provider for open-source models. In AI inference, quality, latency, reliability, and privacy vary a lot. Fireworks has earned our t
This post from Clem Delangue (CEO of Hugging Face) argues that the current state of AI development makes self-hosting open-source language models a viable and advantageous alternative to relying on pa
arXiv:2602.14147v2 Announce Type: replace Abstract: Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multi
Phoebe Liu / The Information: Nvidia and AI chip startup d-Matrix are combining their hardware in a new system to power AI models, the latest example of Nvidia partnering with rivals — Nvidia has a pl
Storage and egress fees have been one of the biggest cloud lock-in traps in AI. When models and datasets are hard and expensive to move, infrastructure choice stops being a real choice. Today, we’re c
arXiv:2607.05761v1 Announce Type: new Abstract: Modern data-driven marketing relies on large amounts of consumer data, yet collecting such data can be costly, time-consuming, and difficult to scale. T
arXiv:2607.05641v1 Announce Type: new Abstract: Rendering time series as chart images for CNN-based classification has become increasingly common in time-series classification (TSC). However, it remai
We're introducing Provisioned Throughput: reserved inference capacity for frontier open models, with token-based pricing and a 99% uptime SLA. Serverless simplicity, guaranteed capacity, up to 90% low
We're still just scratching the surface of how much better, faster, cheaper we can make inference for open-source models! So super excited to see companies like @zml_ai by @steeve come out of stealth
arXiv:2607.03528v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as critical decision-making components in high-stakes real-world AI systems, rendering LLM reli
arXiv:2603.08387v2 Announce Type: replace Abstract: Micro-expression Action Unit (AU) detection identifies localized AUs from subtle facial muscle activations, providing a foundation for decoding affe
arXiv:2607.02671v1 Announce Type: cross Abstract: Benign overfitting and double descent have come to shape our understanding of generalization in deep learning, establishing that overfitting is not on
arXiv:2607.02643v1 Announce Type: new Abstract: Diffusion-based generative models have transformed visual content synthesis, yet they remain vulnerable to unauthorized usage and lack reliable attribut
arXiv:2607.04816v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have become a promising paradigm for generalist robot manipulation, where visual-language representations are used t
arXiv:2602.24264v2 Announce Type: replace Abstract: Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems. Although mod
arXiv:2607.04809v1 Announce Type: cross Abstract: Tabular Foundation Models (TFMs) have demonstrated strong empirical performance as black-box inference engines through in-context learning. However, t
arXiv:2607.03899v1 Announce Type: new Abstract: Diffusion models have become a dominant paradigm for conditional image generation, yet existing approaches generally follow two directions: task-specifi
arXiv:2607.04636v1 Announce Type: new Abstract: Key Information Extraction (KIE) converts visually rich documents into structured data, but practical deployment remains challenging: strong performance
arXiv:2607.02623v1 Announce Type: new Abstract: Time series foundation models (TSFMs) have shown strong zero-shot forecasting performance, but their generalization in covariate-driven, non-stationary
arXiv:2607.04461v1 Announce Type: new Abstract: Inference-time scaling for text-to-image generation has progressed from simple Best-of-N (BoN) sampling to guided search methods that verify and steer c
arXiv:2512.24780v2 Announce Type: replace Abstract: Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specializat
arXiv:2607.04652v1 Announce Type: new Abstract: Learning manipulation from few demonstrations requires visual priors that capture not only where to interact, but also how the interaction should begin;
arXiv:2506.19136v4 Announce Type: replace Abstract: We show that the out-of-equilibrium driving protocol of score-based generative models (SGMs) can be learned via local learning rules. The gradient w
arXiv:2607.03517v1 Announce Type: cross Abstract: Brownian Bridge Diffusion Models (BBDM) offer an appealing framework for image restoration and inverse problems by constructing a stochastic bridge fr
Implementing a data and model monitoring solution is necessary to maintain prediction accuracy and help achieve the best outcome for your machine learning use case. This post shows how you can use ope
arXiv:2607.03925v1 Announce Type: new Abstract: EEG foundation models have shown strong potential in learning generalized representations across subjects and tasks. However, most existing approaches f
arXiv:2607.04775v1 Announce Type: cross Abstract: Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications. While the statistica
arXiv:2607.04332v1 Announce Type: new Abstract: In this paper, we consider the setting where large language models (LLMs) are trained using reinforcement learning (RL) to simultaneously improve reason
arXiv:2607.03039v1 Announce Type: new Abstract: Neural networks are increasingly used to infer hidden physical structure from dynamical observations, yet it remains unclear whether their out-of-distri
arXiv:2607.02914v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness,
arXiv:2607.04163v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answ
arXiv:2607.05353v1 Announce Type: cross Abstract: Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs). Existing approaches include zero-
Fanny Potkin / Reuters: Sources: Beijing recently held meetings with Alibaba, ByteDance, Z.ai, and others to discuss restricting overseas access to advanced open and closed AI models — Chinese authori
Sovereign AI strategies of all types are built on the assumption of continuous releases of open weights models that keep pace with the frontier, giving cost/privacy/control gains at the expense of onl
Super-fun in-depth discussion 🙏🙏🙏 World models, JEPA vs generative architectures, anti-collapse methods for JEPA SSL including contrastive, distillation, and information maximization methods, an expla
This is a key reason I don’t expect the flow of frontier open weights models to continue indefinitely, or even for very much longer. https://www.reuters.com/world/beijing-is-looking-curbing-overseas-a
arXiv:2607.03005v1 Announce Type: new Abstract: In high-dimensional Ising model estimation, target sample sizes are often limited, and effectively using auxiliary binary datasets of unknown relevance
arXiv:2607.04430v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in question answering (QA) systems, yet they may generate hallucinated or misaligned responses wi
arXiv:2503.06269v3 Announce Type: replace-cross Abstract: Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targete
arXiv:2607.02819v1 Announce Type: cross Abstract: Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers.
We sat down with @ylecun for a 1h30 discussion on world models @medjawii and JB Kempf of @videolan/@FFmpeg. It's probably the deepest technical discussion on the subject ever recorded. And we added En
arXiv:2607.03551v1 Announce Type: new Abstract: Weight space learning aims to learn representations of neural network (NN) weights, enabling different downstream tasks. Existing approaches show promis
my friends are all feeling extremely productive and also extremely drained with the latest coding models. this makes me feel like something is wrong, and also that there might be a big opportunity. do
Hugging Face is partnering to make open agent traces available as training data for developing next-generation open-source coding models. This collaboration enables developers to upload agent traces,
The funding headline is only half the story. Yann LeCun told BBC that large language models are not a path to human-like or animal-like intelligence... #AI https://stechtimes.com/en/article/yann-lecun
Happy July 4th everyone 🇺🇸 250 years ago, our founding fathers did not have access to frontier models. (Alexander Hamilton wrote 51 of the 85 Federalist papers. Imagine how many he would've written if
Open-source AI models provide users with full control, customization capabilities, and data ownership, addressing privacy and autonomy concerns compared to proprietary alternatives. The post highlight
A big part of how the team at Runway is able to build and train the models we do and serve the inference demand we have is that we've built incredibly robust research infrastructure and tooling for al
At Cohere we deploy our models directly to our customers, instead of them sending data to us. It makes our job harder, but their business more secure: “When you’re using a consumer app, they are using
arXiv:2603.18315v2 Announce Type: replace-cross Abstract: Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse collision signals, which fail to capture the ric
arXiv:2606.12623v3 Announce Type: replace-cross Abstract: Personalized medicine in acute ischemic stroke requires moving beyond average treatment effects (ATE) to individualized treatment effect (ITE)
Reuters: India's IT secretary said the country is investigating a data breach at Apple supplier Tata, which exposed files that included photos of iPhone 18 Pro models — India is investigating a data b
arXiv:2504.12317v2 Announce Type: replace Abstract: Scientific language is a central infrastructure of knowledge production, but it remains unclear whether large language models (LLMs) are altering no
arXiv:2501.07892v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance in automated code generation, with few-shot prompting widely used for its simplicit
arXiv:2607.02291v1 Announce Type: new Abstract: Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results