Knowledge catalogue
arXiv:2610.13024v1 Announce Type: cross Abstract: World Action Models (WAMs) inherit powerful priors from pretrained video generation models, but their variational autoencoder (VAE) representations ar
arXiv:2610.05031v2 Announce Type: replace Abstract: Large language models are increasingly used as integration layers above specialized tools, but a stronger component does not necessarily produce a s
arXiv:2610.12876v1 Announce Type: cross Abstract: Mixed-integer programming (MIP) solvers are widely used, yet their performance can vary substantially even under seemingly neutral perturbations. Such
arXiv:2610.12727v1 Announce Type: cross Abstract: Feed-forward 3D foundation models reconstruct scenes from unposed images, but the quadratic cost of global attention limits their scalability to large
arXiv:2610.13605v1 Announce Type: new Abstract: Dynamic vocabularies built on-the-fly via Lempel-Ziv-Welch (LZW) compression let a language model represent the same text in fewer tokens, but prior wor
On October 11 2026 François Chollet announced that he has been experimenting with large‑language‑model post‑training techniques using KerasHub, JAX, and TPUs. He indicated that portions of his work ma
Pay close attention to custom harnesses. This is a super interesting paper showing the impact of training inside the harness. Qwen3-14B goes from 22.2% to 54.8% on Spider 2.0-SQLite when it is trained
arXiv:2610.11082v1 Announce Type: cross Abstract: The kernel bandit problem consists of sequentially optimizing an unknown function with noisy feedback, where the function has bounded norm in a given
arXiv:2610.11022v1 Announce Type: cross Abstract: Skillful prediction of biomass-burning activity several days in advance is important for air-quality forecasting and aerosol prediction. Two operation
arXiv:2610.12073v1 Announce Type: cross Abstract: Vision-based tactile sensors provide rich contact information, but processing high-resolution images can be costly for resource-constrained platforms
arXiv:2511.05940v3 Announce Type: replace-cross Abstract: Score-based diffusion models have emerged as a powerful class of generative methods, with successful applications across diverse domains. Desp
arXiv:2610.12118v1 Announce Type: new Abstract: Automated methods have been proposed to overcome the limitations of human verbal deception detection, but evidence remains fragmented across disciplines
arXiv:2610.11054v1 Announce Type: new Abstract: Soft pneumatic actuators are widely used in soft robotics. However, their actuation modes are typically fixed by internal chamber designs or reinforceme
arXiv:2510.26623v2 Announce Type: replace Abstract: Stochastic state estimation methods for continuum robots (CRs) often struggle to balance accuracy and computational efficiency. While several recent
arXiv:2610.12306v1 Announce Type: new Abstract: Learning and problem solving depend critically on the structure of internal representations. While many modern data-driven artificial systems achieve st
arXiv:2610.12132v1 Announce Type: cross Abstract: Predicting the structure and response of inhomogeneous polymer electrolytes requires a description of ion correlations that retains molecular-scale ac
arXiv:2504.12392v3 Announce Type: replace-cross Abstract: Archetypal analysis (AA) was originally proposed in 1994 by Adele Cutler and Leo Breiman as a computational procedure for extracting distinct
arXiv:2502.16412v3 Announce Type: replace Abstract: This paper presents a comprehensive review of industrial anomaly synthesis (IAS). Existing surveys on industrial anomalies mainly focus on anomaly d
arXiv:2610.11139v1 Announce Type: cross Abstract: Anchored Langevin dynamics (ALD) is useful for non-smooth sampling where the density of the target distribution is possibly non-differentiable and hea
arXiv:2610.11003v1 Announce Type: new Abstract: Accurate bone registration is essential for orthopedic surgical navigation and robotic assistance. In a common workflow, the surgeon needs to identify a
arXiv:2610.11436v1 Announce Type: new Abstract: An answer judge instructed to grade the final commitment should reject an explicitly wrong final value even when an earlier value matches the reference.
arXiv:2610.12182v1 Announce Type: cross Abstract: Very-high-resolution Earth-observation satellites acquire more data than they can store and downlink, while in maritime surveillance the vessels cover
Ai2 joined COLM 2026 to share advances in open language models, training infrastructure, and AI for science, including Olmo Hybrid, Asta, and Bolmo, while connecting with the broader research communit
arXiv:2610.10946v1 Announce Type: new Abstract: Large language models (LLMs) are entering wildfire management, where overstated evaluations can cost property and lives. How do they perform on wildfire
arXiv:2610.11537v1 Announce Type: cross Abstract: Flow models generate trajectories from an initial distribution to a target distribution by solving an ordinary differential equation defined by a velo
arXiv:2610.12129v1 Announce Type: new Abstract: A large body of research measures model coherence based on output variance without adequately considering competing causes. We identify two such causes,
arXiv:2508.08833v4 Announce Type: replace-cross Abstract: Frontier large language models (LLMs) now reach near-ceiling accuracy on standard mathematical-reasoning benchmarks and gold-medal-level perfo
arXiv:2606.12590v2 Announce Type: replace-cross Abstract: Preference optimization is increasingly used to post-train medical large vision-language models (LVLMs), yet it operates at a much coarser gra
arXiv:2610.12336v1 Announce Type: cross Abstract: Many tasks in scientific computing and machine learning require the Jacobian or Hessian matrix of a function. Automatic differentiation (AD) computes
arXiv:2610.11238v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in image generation, yet tracing their outputs to individual training examples remains challenging. Ex
arXiv:2610.11162v1 Announce Type: new Abstract: Large pretrained clinical models provide a practical way to reuse learned prior knowledge across hospitals by adapting models to them. In practice, a ta
arXiv:2610.11666v1 Announce Type: cross Abstract: Universal multimodal retrieval typically encodes a query once and ranks independently indexed items by embedding similarity. This design supports effi
arXiv:2511.02374v2 Announce Type: replace-cross Abstract: Current large language models excel at broad, general-purpose tasks, but consistently underperform when exposed to highly specialized domains
arXiv:2610.10875v1 Announce Type: new Abstract: Motivated by recent applications in generative modeling and sampling, we introduce a framework for optimal measure transport where cost captures the not
arXiv:2610.12150v1 Announce Type: new Abstract: In many engineering design problems, the objective and constraints depend on the state: the solution of a PDE determined by the design parameters. We co
arXiv:2610.11362v1 Announce Type: cross Abstract: Binary diffusion models typically require a large number of function evaluations (NFEs) to generate high-quality samples, making practical inference c
arXiv:2610.11627v1 Announce Type: new Abstract: Repairing scientific models from functional observations differs fundamentally from supervised prediction: feedback may certify a solution without revea
arXiv:2610.11759v1 Announce Type: cross Abstract: Near-term quantum approaches to combinatorial optimization are limited by qubit counts, circuit fidelity, sampling cost, and the difficulty of encodin
arXiv:2610.11501v1 Announce Type: new Abstract: Despite the adoption of large language models (LLMs) in recommendation systems, prevailing approaches mostly model single-type behaviors (e.g., views or
arXiv:2610.12421v1 Announce Type: new Abstract: Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth motion and rigid geometry. While effec
arXiv:2610.12449v1 Announce Type: cross Abstract: Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep le
arXiv:2602.07535v2 Announce Type: replace-cross Abstract: Acute ischemic stroke requires rapid treatment decisions that are strongly guided by emergency imaging. Admission computed tomography perfusio
arXiv:2610.11218v1 Announce Type: cross Abstract: Dense associative memory (DAM) provides an energy-based framework for memory retrieval with close connections to attention mechanisms in modern artifi
arXiv:2610.12307v1 Announce Type: new Abstract: Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-sized image patches. This static pa
arXiv:2610.11549v1 Announce Type: new Abstract: Acquiring realistic microstructure data through Electron Backscatter Diffraction (EBSD) is costly and time consuming, often relying on specialised equip
arXiv:2509.16525v2 Announce Type: replace-cross Abstract: Machine learning models are increasingly deployed as software components that must evolve as requirements change. When specific training recor
arXiv:2610.10793v1 Announce Type: cross Abstract: Distributionally robust optimization (DRO) protects decisions against distributional uncertainty by optimizing over an ambiguity set, but poorly align
arXiv:2610.11683v1 Announce Type: new Abstract: Fusing a learned camera-noise fingerprint with an RGB appearance backbone is an appealing route to generator-independent deepfake detection, because the
arXiv:2604.05716v2 Announce Type: replace Abstract: LLMs have shown strong potential to advance scientific discovery. Whether they possess the capacity for foundational innovation, however, remains an
arXiv:2610.11153v1 Announce Type: cross Abstract: Fine-grained visual classification requires models to recognize subtle local traits while exposing the visual evidence behind their predictions. Class
arXiv:2610.12445v1 Announce Type: cross Abstract: Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception d
arXiv:2610.11163v1 Announce Type: cross Abstract: Third-party challenge-response identity verification (TP-CRIV) enables an independent verifier to assess whether a claimant possesses a model identica
arXiv:2610.10724v1 Announce Type: new Abstract: How does the human mind represent semantic categories? Why do natural languages favor certain meanings over others? Prior explanations have relied on lo
arXiv:2610.11306v1 Announce Type: new Abstract: Adversarial distillation transfers robustness from high-capacity teachers to compact students. Existing adversarial distillation methods mainly use teac
arXiv:2610.11784v1 Announce Type: new Abstract: Tabular in-context learning (ICL) has emerged as a training-free and accurate paradigm for tabular prediction, but current approaches to compressing its
arXiv:2610.12008v1 Announce Type: new Abstract: Abstract argumentation frameworks (AFs) introduced by Dung provide a formal foundation for non-monotonic reasoning in artificial intelligence. While dec
arXiv:2610.12328v1 Announce Type: new Abstract: We consider stochastic nonsmooth nonconvex composite optimization, which includes several important problems such as constrained optimization and the re
arXiv:2610.11548v1 Announce Type: new Abstract: Synthetic tasks are increasingly used both as probes of language-model capability and as pretraining data. Both uses are often justified by loss reducti
arXiv:2610.10829v1 Announce Type: cross Abstract: Conformal prediction provides prediction sets with finite-sample guarantees, but the label verification required for calibration can be expensive. We
arXiv:2602.03538v2 Announce Type: replace Abstract: While Dynamic Gaussian Splatting enables high-fidelity 4D reconstruction, its deployment is severely hindered by a fundamental dilemma: unconstraine