Knowledge catalogue
Mistral Large 4 against the field: efficiently reasoning over diverse complex challenges. CTF speedrun: 19 challenges, with tool calls and solve times grounded in actual runs. It solved 18 of the 19.
Mistral AI announced that its new model, Mistral Large 4, is among the world's most powerful AI systems specifically designed for cybersecurity tasks. The tweet shared on October 6, 2026 highlights th
Carl Franzen / VentureBeat: Mistral launches a preview of Mistral Large 4, or Le Chonk, a 1T model it claims tops any open model developed in the US or Europe; weights are due October 27 — Mistral is
Mistral AI SAS today opened access to Mistral Large 4, its most capable large language model to date. On launch, the LLM is available in public preview through the company’s cloud platform. Mistral pl
Sabrina Ortiz / The Deep View: Mistral releases Mistral Large 4, dubbed “le Chonk”, a 1T-parameter open-weight model for general agentic capabilities, trained on 4,000 Grace Blackwell GPUs — Most flag
Mistral Blog: Mistral says it trained ML4 “from scratch” using 3,800 Nvidia Grace Blackwell GPUs in its data centers in Europe and much of its training data was multilingual — Le Chonk — Today, we're
arXiv:2610.04157v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) often struggle to capture long-range dependencies due to over-squashing -- a phenomenon in which the repeated compression
arXiv:2610.04307v1 Announce Type: cross Abstract: Machine Learning (ML) methods promise a fast solution process for Optimal Power Flow (OPF). While inconsistent test cases, implementations, and evalua
arXiv:2510.13276v2 Announce Type: replace Abstract: The rapid advancement of long-context vision language models (LCVLMs) has led to a significant expansion of their context windows. However, an exten
arXiv:2610.05289v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have achieved remarkable performance in novel view synthesis, yet deploying both static and dynamic Gaus
arXiv:2610.06210v1 Announce Type: new Abstract: Autoregressive generation is natural for language, where predicted tokens can be directly reused as the next prediction state, but trajectory forecastin
guys do you still remember K2 Horizon? https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B-GGUF https://huggingface.co/IFM/K2-Horizon-32B-GGUF https://huggingface.co/IFM/K2-Horizon-3.7B-GGUF https://hu
arXiv:2610.04310v1 Announce Type: new Abstract: Machine unlearning is seen as a promising approach to enable users to exercise the 'right to erasure' in the context of AI models. We ask how users migh
arXiv:2503.09950v2 Announce Type: replace Abstract: In this paper, we address the problem of human trajectory forecasting, which aims to predict the inherently multi-modal future movements of humans b
arXiv:2610.05595v1 Announce Type: cross Abstract: Local Gaussian models of constant-step learning predict output variability and expected losses, but weak convergence alone does not justify these mome
arXiv:2610.04914v1 Announce Type: cross Abstract: Monitoring the chain-of-thought (CoT) of large reasoning models (LRMs) is a common way to detect misbehavior in real-world practice. However, current
arXiv:2610.05552v1 Announce Type: new Abstract: Three-dimensional gait analysis guides rehabilitation after spinal cord injury but depends on marker-based motion capture and force plates, which few cl
arXiv:2610.03898v1 Announce Type: new Abstract: Model-based control of an aquatic robotic platform depends on a hydrodynamic model that is costly to identify and specific to the hull, payload, and con
arXiv:2411.12426v3 Announce Type: replace Abstract: Real-world applications of stereo matching, such as autonomous driving, place stringent demands on both safety and accuracy. However, learning-based
arXiv:2610.04814v1 Announce Type: new Abstract: Segment-based explanation methods such as LIME return a single explanation for each prediction, computed from one fixed image segmentation. This hides t
arXiv:2610.06378v1 Announce Type: new Abstract: The rapid evolution of video generation has narrowed the perceptual gap between authentic and synthetic videos, making generalizable AI-generated video
arXiv:2512.12694v2 Announce Type: replace-cross Abstract: Large multilingual knowledge bases expose temporally diverse information, yet retrieval quality remains sensitive to lexical variation and cro
arXiv:2601.13886v2 Announce Type: replace Abstract: Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial p
arXiv:2610.05882v1 Announce Type: cross Abstract: Learning from human demonstrations is a reliable way to teach robots new tasks, but the gains from each additional demonstration shrink as the policy
arXiv:2610.04802v1 Announce Type: new Abstract: This project explores how multiple cognitive radars can learn to share limited wireless spectrum with other radio users without interfering with one ano
arXiv:2610.04456v1 Announce Type: new Abstract: Deep learning models for crop leaf disease recognition routinely report near-perfect accuracy yet are typically trained and evaluated on a single datase
arXiv:2510.16587v2 Announce Type: replace-cross Abstract: Understanding the continuous evolution of populations from discrete temporal snapshots is a critical research challenge, particularly in field
arXiv:2610.06389v1 Announce Type: new Abstract: Super-resolution and semantic segmentation are known to benefit one another, especially in the Earth observation context. However, learning both tasks i
arXiv:2603.27170v2 Announce Type: replace Abstract: Relative camera pose is a basic geometric cue for visual re-localization and scene understanding. When using images alone, visual evidence may not s
arXiv:2610.06365v1 Announce Type: new Abstract: Sinkholes are a widespread geohazard in karst terrain. In Florida, soluble carbonate bedrock, shallow groundwater, and intense rainfall combine to make
arXiv:2610.06602v1 Announce Type: new Abstract: Early osteoarthritis detection through quantitative MRI (qMRI) requires accurate cartilage and meniscus segmentation, traditionally necessitating time-c
arXiv:2607.17938v2 Announce Type: replace Abstract: Object-level mapping and topological navigation reason about whole objects, yet the correspondences they rely on are computed over keypoints or pixe
arXiv:2610.04722v1 Announce Type: new Abstract: Sparse-view novel view synthesis is a central problem in 3D content creation, but diffusion-based approaches remain limited by iterative denoising, maki
arXiv:2610.04944v1 Announce Type: cross Abstract: We characterize, up to logarithmic factors, the minimax expected query complexity of finite-sum nonconvex-strongly-concave optimization under mean-squ
Enterprises sitting on decades of legacy information face a pressing question as artificial intelligence moves from pilots to production: Can that archive become AI-ready data without a costly rebuild
Enterprises and individual developers frequently run multiple AI inference models. The right architecture can simplify how the models are called while also providing centralized governance. In this po
arXiv:2610.05542v1 Announce Type: new Abstract: Control barrier functions are an effective model-based tool to formally certify the safety of a system. However, transferring their theoretical guarante
arXiv:2510.03614v2 Announce Type: replace Abstract: Sequential estimation under partial observability requires tracking beliefs that may be high-dimensional, multimodal, and non-Gaussian. Classical Ba
arXiv:2610.06502v1 Announce Type: new Abstract: Content-based image retrieval (CBIR) in neuroimaging enables the identification of structurally similar brain scans, supporting diagnosis, prognosis, an
arXiv:2610.04551v1 Announce Type: new Abstract: Multiple LiDAR-inertial odometry methods have been widely applied in robotic applications owing to their enhanced accuracy and reliability. However, ado
arXiv:2610.05401v1 Announce Type: new Abstract: Text-to-image diffusion models can generate prohibited content, which motivates concept erasure through machine unlearning. Most erasure methods interve
arXiv:2610.05919v1 Announce Type: new Abstract: Seizure monitoring and detection are crucial for reducing the morbidity and mortality associated with seizures. Current epilepsy care, often involving e
arXiv:2610.04545v1 Announce Type: cross Abstract: This paper presents a nonlinear extension of Density-Driven Optimal Control (D2OC) for multi-agent spatial coverage with prescribed density distributi
arXiv:2610.05081v1 Announce Type: new Abstract: Teleoperation is becoming increasingly important for collecting high-quality demonstrations to teach robots dexterous manipulation skills. For dexterous
arXiv:2610.04924v1 Announce Type: new Abstract: Visually identical containers can conceal loads that require different handling decisions. We present TANav, which uses a brief nudge to measure push re
arXiv:2502.06359v3 Announce Type: replace Abstract: Ensuring safe driving while maintaining travel efficiency for autonomous vehicles in dynamic and occluded environments is a critical challenge. This
arXiv:2512.15621v2 Announce Type: replace Abstract: Occupancy world models use historical occupancy states to forecast future 3D scenes, but their robustness under corrupted temporal inputs remains po
arXiv:2610.06259v1 Announce Type: new Abstract: Partial differential equation (PDE) inverse problems are often ill-posed, making fine-scale details difficult to recover. We address this problem by int
arXiv:2610.04281v1 Announce Type: new Abstract: Lossless triangle mesh compression must preserve both vertex positions and connectivity. Octrees support learned point cloud geometry coding and progres
arXiv:2610.06469v1 Announce Type: new Abstract: Closed-loop evaluation of end-to-end driving requires continuous rollouts that reveal how earlier decisions affect subsequent driving. However, existing
arXiv:2610.05872v1 Announce Type: new Abstract: A long-standing goal of AI is a model that can continually learn and improve itself. On post-trained models, supervised finetuning (SFT) on new data oft
arXiv:2610.05878v1 Announce Type: new Abstract: Benchmarks expose vision-language-action (VLA) policies to few canonical instructions, while exhaustive deployment testing is impossible. We introduce O
Ollama Cloud Model pricing monitor with tabled costs and calculator. https://kasp0r.github.io/ollama_cloud_models_comparison https://preview.redd.it/hxbpnuq7quth1.png?width=1372&format=png&auto=webp&s
arXiv:2610.04067v1 Announce Type: new Abstract: In this paper, we unravel the effect of different decoder architectures on the interpretability of the latent space of the Physically Recurrent Neural N
arXiv:2610.05902v1 Announce Type: cross Abstract: 'Don't tune hyperparameters on the test set' is often stated in machine learning textbooks. Violating it is considered a cardinal sin that produces mi
arXiv:2610.06139v1 Announce Type: cross Abstract: Melanoma is the deadliest type of skin cancer, whose early diagnosis is crucial for patients' survival. Image classification using deep learning model
arXiv:2610.06777v1 Announce Type: cross Abstract: The CADENCE algorithm solves the Partially Observable Cooperative Guard Art Gallery Problem (POCGAGP) with formal coverage and connectivity guarantees
arXiv:2610.05186v1 Announce Type: cross Abstract: We prove that no single rank ordered adversary strategy is globally optimal for the prediction with expert advice problem with six or more experts, in
arXiv:2610.05338v1 Announce Type: new Abstract: Hierarchical reinforcement learning uses temporally extended subtasks for exploration, yet committing to their execution can restrict both deployment an
arXiv:2101.01631v2 Announce Type: cross Abstract: We demonstrate that from an algorithm guaranteeing an approximation factor for the ratio of submodular (RS) optimization problem, we can build another