Knowledge catalogue
arXiv:2606.23572v1 Announce Type: new Abstract: We develop a spectral theory for normalized corrected GNN propagation. The object of study is the symmetric normalized adjacency with its degree-station
arXiv:2507.07907v2 Announce Type: replace-cross Abstract: Learning is a complex dynamical process shaped by a range of interconnected decisions. Careful design of hyperparameter schedules for artifici
arXiv:2606.21304v1 Announce Type: new Abstract: This paper introduces the CERTH-ITI solution for the MediaEval NewsImages 2026 challenge, which focuses on generating images related to news headlines.
arXiv:2606.21220v1 Announce Type: new Abstract: Inspection of offshore wind turbine rotor blades is critical for predictive maintenance to maximise efficiency and extend operational lifetime. However,
arXiv:2606.20620v1 Announce Type: new Abstract: Starting from the axiomatic formulation of scale-space theory, we develop a viscosity-solution framework for multiscale image representations arising fr
arXiv:2606.21528v1 Announce Type: cross Abstract: We study first-order methods for solving monotone variational inequalities arising in min-max optimization. Classical approaches such as the extragrad
arXiv:2606.22112v1 Announce Type: new Abstract: The performance of advanced materials for extreme environments is underpinned by their microstructure, including the size and distribution of reinforcin
arXiv:2503.01290v3 Announce Type: replace Abstract: Predicting post-intervention distributions from observational data is central to many scientific and decision-making problems, but remains challengi
arXiv:2606.22277v1 Announce Type: cross Abstract: We study trajectory optimization in mobile sensing systems that must identify which member of a finite candidate set is the true target, while maintai
arXiv:2606.21713v1 Announce Type: cross Abstract: In X-ray tomography, reconstruction quality generally improves with larger numbers of projections. However, more projections increase experiment costs
arXiv:2606.23359v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) provide an effective way to solve partial differential equations (PDEs) by embedding physical principles into t
arXiv:2606.19891v2 Announce Type: replace Abstract: We study adversarial bandit optimization in which the loss functions may be non-convex and non-smooth. In each round, the learner selects an action
arXiv:2606.21892v1 Announce Type: cross Abstract: Crop recommendation systems in precision agriculture have long suffered from a fundamental modality gap: visual soil characterization and chemical nut
arXiv:2503.00366v3 Announce Type: replace-cross Abstract: Thyroid scintigraphy is vital for diagnosing thyroid disorders, yet deep learning (DL) models in this domain often struggle with limited, imba
AI in 2040 will not be built on the stack we are using today. It will be much closer to optimal. The current stack has 3-4 orders of magnitude of data inefficiency and 4-5 orders of magnitude of compu
arXiv:2410.07397v2 Announce Type: replace Abstract: As data-driven modeling of physical dynamical systems becomes more prevalent, a new challenge is emerging: making these models more compatible and a
arXiv:2606.22325v1 Announce Type: new Abstract: Attention sinks, representation collapse, and norm stratification are treated as transformer-specific pathologies. We show they are not specific to atte
arXiv:2606.20738v1 Announce Type: new Abstract: This article presents a complementary approach for integrating multimodal medical data in cancer classification, based on state space models represented
arXiv:2606.21257v1 Announce Type: new Abstract: OpenPangu models are attractive targets for private and domestic large-language-model deployment, yet their robustness under aggressive post-training qu
arXiv:2603.05544v2 Announce Type: replace-cross Abstract: Proper scoring rules are essential for evaluating probabilistic forecasts. We propose a simple algebraic rearrangement of the Yates covariance
arXiv:2606.23550v1 Announce Type: cross Abstract: In this work, Neural ODEs equipped with a curated collection of equilibrium points have been successfully employed for classification tasks.The plante
arXiv:2606.23514v1 Announce Type: new Abstract: Text and image conditioned 3D models now generate convincing assets, but they still offer little direct control over the space an object should occupy o
arXiv:2606.21209v1 Announce Type: cross Abstract: We present an iterative algorithm to compute an arc-length parameterized spline interpolating a set of points. This differs from other methods where t
arXiv:2606.21701v1 Announce Type: cross Abstract: Long-term records of the Martian atmosphere based on general circulation models and reanalysis of atmospheric state variables are important to underst
arXiv:2606.21938v1 Announce Type: new Abstract: Reconstructing articulated objects from sparse images requires recovering complete geometry, movable parts, and motion parameters. Recent methods typica
arXiv:2507.10443v3 Announce Type: replace-cross Abstract: The Hopfield network made associative memory (AM) the model system of neural computation, but it solves the problem only for a stationary worl
arXiv:2606.22406v1 Announce Type: new Abstract: Attention mechanisms have demonstrated remarkable empirical success in identifying relevant information from large collections of tokens, yet the theore
arXiv:2604.01989v3 Announce Type: replace Abstract: Like a body at rest that stays at rest, we find that visual attention in multimodal large language models (MLLMs) exhibits pronounced inertia, remai
arXiv:2606.23251v1 Announce Type: cross Abstract: High-fidelity simulations of free-surface flows using Lagrangian methods such as the Particle Finite Element Method (PFEM) are computationally demandi
arXiv:2606.23063v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly required to adapt to non-stationary streams of visual domains, question types, and user instru
arXiv:2606.22608v1 Announce Type: new Abstract: Learning to read cuneiform tablets is an extremely demanding task; consequently, of the roughly half million excavated tablets, only a small fraction ha
arXiv:2606.23542v1 Announce Type: new Abstract: Forest imagery analysis often involves multiple tightly coupled vision tasks, which must be performed under substantial variation in geographic regions,
arXiv:2606.21279v1 Announce Type: new Abstract: Nowadays, more and more disasters of different natures are appearing. Several disaster assessment approaches have been developed in order to identify da
arXiv:2606.21838v1 Announce Type: new Abstract: Multimodal contrastive learning has enabled zero-shot visual classification by aligning images with textual categories. However, in hierarchically struc
arXiv:2606.20678v1 Announce Type: cross Abstract: Mechanistic interpretability methods summarize a transformer component by a single importance score, conflating two distinct roles: a component may ma
arXiv:2606.20680v1 Announce Type: new Abstract: A biometric verifier is often deployed with a strict false match budget, so only a narrow, low false match rate (FMR) slice of the score range is used.
arXiv:2606.21775v1 Announce Type: new Abstract: Recently, world models have emerged as a promising paradigm for building intelligent agents by learning predictive models that estimate future environme
arXiv:2606.22515v1 Announce Type: new Abstract: Sexual identification of decomposed cadavers challenges traditional methods dependent on visual anthropological analysis. This study evaluates state-of-
arXiv:2606.22138v1 Announce Type: cross Abstract: We present BioMatrix, the first multimodal foundation model that natively integrates sequences, structures, and natural language for both molecules an
arXiv:2606.21398v1 Announce Type: new Abstract: Vision-Language Models (VLMs) for embodied navigation rely on selecting a fixed number of frames from a growing trajectory history. As episodes extend,
arXiv:2606.23023v1 Announce Type: new Abstract: Although state-of-the-art neural video codecs (NVCs) have achieved remarkable performance, they suffer from limited generalization when encountering com
arXiv:2606.21594v1 Announce Type: new Abstract: Recent advances in large pre-trained models have led to remarkable progress in instance segmentation on general images. However, industrial scenarios re
arXiv:2505.11495v2 Announce Type: replace Abstract: Push recovery during locomotion will facilitate the deployment of humanoid robots in human-centered environments. In this paper, we present a unifie
arXiv:2606.23494v1 Announce Type: new Abstract: Automated diagnosis of 3D brain CT scans is essential for critical care, yet it remains challenging due to the heavy reliance on manual annotations and
arXiv:2606.20644v1 Announce Type: cross Abstract: Multi-objective shortest-path (MOSP) algorithms traditionally rely on single-valued heuristics (SVHs), which associate each state with a single admiss
arXiv:2606.23157v1 Announce Type: new Abstract: This paper presents a modular training-free framework for zero-shot, language-guided robotic manipulation in semi-structured environments. The architect
arXiv:2606.23473v1 Announce Type: new Abstract: Universal segmentation models exhibit significant potential for diverse tasks involving different imaging modalities and segmentation objectives. Task-I
arXiv:2606.16214v3 Announce Type: replace Abstract: Modern deep learning models remain notoriously prone to overconfidence, limiting their reliability in high-stakes applications. Bayesian methods aim
arXiv:2606.22085v1 Announce Type: cross Abstract: There are many reasons one may want to edit a model's chain of thought (CoT) -- e.g., to prefill it with reasoning from a stronger model or to remove
arXiv:2606.22987v1 Announce Type: new Abstract: Single-view mesh reconstruction predicts object meshes and spatial layouts from a single observation, making it attractive for fast robot spatial reason
Francois Chollet presents a framework for understanding different approaches to token usage in AI models: casual users maximize tokens for flexibility, competitive users minimize tokens for efficiency
arXiv:2412.06190v2 Announce Type: replace Abstract: Benefiting from the generalization capability of CLIP, recent vision language pre-training (VLP) models have demonstrated the ability to capture a w
arXiv:2606.23280v1 Announce Type: new Abstract: Automated Reward Design (ARD) aims to replace manual reward engineering in reinforcement learning with language-driven reward function synthesis. Howeve
arXiv:2606.21806v1 Announce Type: new Abstract: Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains. A common sourc
arXiv:2606.21433v1 Announce Type: cross Abstract: In this article, we analyse convergence of the averaged Adam optimizer to an attracting zero of the Adam vector field. We provide a central limit theo
arXiv:2606.13092v2 Announce Type: replace Abstract: Scale buys interpolation; structure buys certifiable transfer. A world model's average error does not say whether a particular rollout can be truste
C’est elle qui a jeté Fauci en pâture relayé ensuite par RFK et Musk… Je vous le dis Le RN au pouvoir ça sera ça. On peut ne pas être content. Vouloir du changement. Mais le changement ça peut être en
arXiv:2606.20747v1 Announce Type: new Abstract: Explainable Artificial Intelligence aims to make black-box models more trustworthy by presenting, in a human-understandable manner, the elements that le
arXiv:2509.13793v2 Announce Type: replace-cross Abstract: It is shown that the port behavior of a resistor-diode network corresponds to the solution of a ReLU monotone operator equilibrium network (a
arXiv:2606.12966v2 Announce Type: replace Abstract: Grokking is the delayed generalisation phenomenon where a transformer trained on modular arithmetic abruptly transitions from near-chance to near-pe