Gemma 4 Technical Report
arXiv:2607.02770v1 Announce Type: cross Abstract: We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute effi
Knowledge catalogue
arXiv:2607.02770v1 Announce Type: cross Abstract: We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute effi
arXiv:2607.05257v1 Announce Type: new Abstract: Origin-destination (OD) flow modeling underpins urban planning and mobility analysis, but prevailing graph-based methods often neglect salient geographi
arXiv:2607.02980v1 Announce Type: cross Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense atte
This article describes how to use Hugging Face models with Microsoft's Foundry Managed Compute infrastructure, likely covering integration steps, deployment options, and the benefits of running open-s
arXiv:2607.02850v1 Announce Type: new Abstract: Meta-learning without labeled data is crucial for real-world applications, where obtaining labeled datasets can be expensive or restricted due to privac
arXiv:2607.04525v1 Announce Type: cross Abstract: How concepts are represented in neural networks is a fundamental question in machine learning. The dominant view treats concept representations as sta
arXiv:2607.03558v1 Announce Type: cross Abstract: Continuous video anomaly detection is dominated by reactive Multiple Instance Learning (MIL) that collapses spatiotemporal features into scalar scores
arXiv:2607.04270v1 Announce Type: cross Abstract: Large language models (LLMs) have recently emerged as powerful backbones for recommender systems by reformulating recommendation as a token-level gene
arXiv:2607.03751v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models acquire broad embodied capabilities through large-scale pretraining, yet their generalization remains far more fragi
arXiv:2607.03644v1 Announce Type: cross Abstract: Decades of orbital missions have produced multi-modal remote sensing data for the Moon, spanning optical imagery, spectroscopy, thermal emission, rada
arXiv:2607.03704v1 Announce Type: new Abstract: Background: Growing individual case safety report (ICSR) volumes have intensified demand for scalable automated causality assessment. Large Language Mod
arXiv:2607.03855v1 Announce Type: new Abstract: We address the inverse problem of blind 3D scene reconstruction from extremely motion-blurred images, a scenario where traditional Structure-from-Motion
arXiv:2510.19698v3 Announce Type: replace Abstract: Large Language Models (LLMs) can propose rules in natural language, sidestepping the need for a predefined predicate space in traditional rule learn
arXiv:2510.17801v2 Announce Type: replace-cross Abstract: Building robots that can perceive, reason, and act in dynamic, unstructured environments remains a central challenge. Recent embodied systems
arXiv:2607.04610v1 Announce Type: new Abstract: Diverse applications for robotics, such as industry and agriculture, require robots to operate across various embodiments, changing visual conditions, a
arXiv:2607.03788v1 Announce Type: new Abstract: Discrete diffusion promises orders-of-magnitude faster generation than autoregressive (AR) models for sequential discrete data, yet its full potential o
arXiv:2502.12096v5 Announce Type: replace-cross Abstract: In this paper, we introduce token communications (TokCom), a large model-driven framework to leverage cross-modal context information in gener
arXiv:2607.04686v1 Announce Type: cross Abstract: Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails. A model that never calls a ne
arXiv:2607.04593v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large
arXiv:2607.05055v1 Announce Type: new Abstract: Healthcare appointment scheduling remains a persistent operational bottleneck, driven by manual coordination, fragmented legacy systems, and high admini
arXiv:2607.02608v1 Announce Type: cross Abstract: Lightweight neuromorphic computing offers a promising route to efficient AI, with particular benefits for resource-constrained edge deployments. Howev
arXiv:2607.04674v1 Announce Type: new Abstract: Recovering dynamic environment maps from a single in-the-wild video is crucial for photorealistic rendering, yet remains a challenge. Recent video gener
Palantir Technologies Inc. Chief Executive Alex Karp’s recent broadside against the frontier model vendors put a knife to the throat of the central enterprise artificial intelligence debate. Karp’s ar
arXiv:2607.02403v1 Announce Type: cross Abstract: Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost ju
arXiv:2509.25136v3 Announce Type: replace Abstract: Activation-aware low-rank factorization techniques yield strong compression results but are generally confined to linear layers, while existing whit
arXiv:2607.01538v1 Announce Type: new Abstract: Language models (LMs) raise an intriguing alternative to vector-based retrieval: conditioning on an in-context corpus and directly generating a relevant
arXiv:2607.02089v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning. Ex
Tesla has begun initial production of the Model Y Long Wheelbase variant at its Gigafactory Texas facility. The Long Wheelbase version offers extended interior space and cargo capacity compared to the
arXiv:2607.01502v1 Announce Type: new Abstract: Recent advances in automatic speech recognition (ASR) have explored different sequence models, including Conformer-based models and newer state space mo
arXiv:2607.02459v1 Announce Type: new Abstract: Language models are increasingly used to quantify cultural phenomena, but what makes such measurement distinctively cultural? This paper argues that NLP
arXiv:2607.02140v1 Announce Type: new Abstract: Chemical language models (CLMs) are trained with linearized representations such as SMILES, yet it remains unclear which chemically meaningful substruct
arXiv:2607.02490v1 Announce Type: new Abstract: Large vision-language models can reason over multimodal inputs by generating textual chains of thought (CoT). A key capability exhibited in CoT reasonin
arXiv:2607.00678v1 Announce Type: new Abstract: Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typi
AI sovereignty isn’t optional. Don’t give away your alpha so easily. Protect it as much as you can. Open source models are critical and should be an important part of any individual’s, organisation’s,
This post critiques Fable AI's text generation style, suggesting it produces overly verbose or exaggerated outputs that parody Claude's characteristic writing patterns taken to an extreme. The comment
arXiv:2607.00862v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) have achieved remarkable success on complex tasks by leveraging long chain-of-thought (CoT) trajectories, yet they frequ
arXiv:2607.01057v1 Announce Type: cross Abstract: We study a broad class of graphical models whose independencies correspond to vertex separation in mixed graphs with directed, undirected, and bidirec
arXiv:2607.00500v1 Announce Type: cross Abstract: Image-guided therapies, including radiotherapy, biopsy and deep brain stimulation, rely on real-time targeting of anatomical structures. However, in t
arXiv:2607.00553v1 Announce Type: cross Abstract: Lightweight machine learning models are increasingly proposed for intrusion detection in Industrial Internet of Things (IIoT) networks due to their su
arXiv:2607.00275v1 Announce Type: cross Abstract: Federated Learning (FL) is a distributed machine learning (ML) paradigm with collaboration among multiple clients without sharing data. FL is challeng
arXiv:2504.06299v2 Announce Type: replace-cross Abstract: Multimodal prediction models based on imaging and clinical data are increasingly used for clinical decision support, yet their interpretabilit
arXiv:2607.01012v1 Announce Type: new Abstract: Data assimilation models state dynamics conditioned on sequential observations, and has wide-ranging scientific applications. In the filtering setting,
arXiv:2606.13695v2 Announce Type: replace-cross Abstract: Mineral prospectivity modelling (MPM) underpins exploration economics, yet most operational pipelines reduce to data-driven classifiers traine
arXiv:2403.19645v2 Announce Type: replace Abstract: The rapid advancement of diffusion models has enabled the generation of high-fidelity images from textual prompts, yet achieving precise, disentangl
arXiv:2607.00700v1 Announce Type: cross Abstract: LLVM is a widely used compiler infrastructure whose scale and complexity make issue resolution labor-intensive and challenging. Although large languag
Lots of people are advocating for more American open-source models these days which is amazing but very few people do anything about it! Latest example, Alex Karp came out advocating for American open
arXiv:2603.22055v2 Announce Type: replace-cross Abstract: Underground mining robots are increasingly modeled for planning, operator training, and digital-twin workflows, where reliable actuator-level
arXiv:2607.00248v1 Announce Type: new Abstract: We present Seed2.0, a model series that takes a meaningful step toward solving complex, real-world tasks. Our approach begins with identifying users' ge
arXiv:2607.00402v1 Announce Type: cross Abstract: Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts. Recent metho
arXiv:2607.00817v1 Announce Type: new Abstract: Text-to-image diffusion models achieve impressive visual quality, yet demographic bias remains a challenge, as neutral prompts consistently produce ster
arXiv:2607.00447v1 Announce Type: new Abstract: Large language models often produce hallucinated answers that violate prompt-level constraints. A key diagnostic question is whether these failures refl
why are the open tools so low in the list? We need to improve integration between open platforms and open models @steipete @thdxr @Teknium @badlogicgames! Coding agents are real users of the @huggingf
arXiv:2606.31483v1 Announce Type: new Abstract: Personalized driving can improve the user acceptance of automated driving systems. However, existing methods still provide limited support for translati
arXiv:2404.10034v3 Announce Type: replace Abstract: Weakly Supervised Object Localization (WSOL) allows training deep learning models for classification and localization (LOC) using only global class-
arXiv:2602.15008v2 Announce Type: replace Abstract: Diffusion models over discrete spaces have recently shown striking empirical success, yet their theoretical foundations remain incomplete. In this p
arXiv:2606.31511v1 Announce Type: cross Abstract: In deployment settings where retraining is infeasible, small frozen code models are routinely asked to repair a failed program after seeing their own
arXiv:2511.17979v2 Announce Type: replace Abstract: Diffusion models have achieved remarkable success in generative modeling, yet how to effectively adapt large pretrained models to new tasks remains
arXiv:2603.12893v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning f
arXiv:2606.31699v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated featu
arXiv:2606.31397v1 Announce Type: cross Abstract: State-based fine-tuning has emerged as a compelling alternative to weight-based adaptation for transformers, updating lightweight controls into states