Knowledge catalogue
arXiv:2605.16348v1 Announce Type: cross Abstract: Training-free guidance enables pre-trained diffusion and flow models to optimize application-specific objectives using feedback from external black-bo
arXiv:2605.18472v1 Announce Type: cross Abstract: Generative models can produce nonsensical text, unrealistic images, and unstable materials faster than simulation or human review can absorb; without
arXiv:2505.16786v2 Announce Type: replace Abstract: We introduce FlowMixer, a single-layer neural architecture that leverages constrained matrix operations to model structured spatiotemporal patterns
arXiv:2605.18155v1 Announce Type: new Abstract: Translating formal language into natural language is a foundational challenge in NLP, driving various downstream applications in semantic parsing, theor
arXiv:2605.18607v1 Announce Type: new Abstract: Progress in language model development is often driven by comparative decisions: which architecture to adopt, which pretraining corpus to use, or which
arXiv:2605.16319v1 Announce Type: new Abstract: Medium-horizon Alzheimer's disease progression prediction is difficult because future clinical scores can remain tied to baseline severity, while biomar
arXiv:2601.06163v2 Announce Type: replace Abstract: The widespread adoption of text-to-image (T2I) diffusion models has raised concerns about their potential to generate copyrighted, inappropriate, or
arXiv:2605.18147v1 Announce Type: new Abstract: Predictive models play a pivotal role in credit risk management, guiding critical decisions through accurate estimation of default probabilities and los
arXiv:2605.16594v1 Announce Type: cross Abstract: In this paper, we develop a physics-informed deep operator learning framework for solving multi-term time-fractional mixed diffusion-wave equations (T
arXiv:2605.16366v1 Announce Type: cross Abstract: Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tok
arXiv:2605.18462v1 Announce Type: new Abstract: Named entity recognition (NER) has been one of the essential preliminary steps in modern NLP applications. This report focuses on implementing the NER t
arXiv:2603.17588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are currently applied to scientific paper evaluation by assigning an absolute score to each paper independently.
arXiv:2605.16928v1 Announce Type: cross Abstract: Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely ei
arXiv:2605.17968v1 Announce Type: new Abstract: We study the approximation of nonlinear operators between function spaces by transformers. Our approach is to lift functions to measures supported on th
arXiv:2605.18010v1 Announce Type: new Abstract: Acquisition and creation of 3D assets have been largely view- or appearance-driven. As a result, existing digital 3D models often lack the requisite str
arXiv:2605.18252v1 Announce Type: new Abstract: We introduce GaussianZoom, a generative zoom-in 3D reconstruction system with an iterative progressive framework that combines geometry-consistent scene
arXiv:2605.17456v1 Announce Type: cross Abstract: Multiple instance learning (MIL) is the standard approach for whole-slide image (WSI) classification and survival prediction, where attention-based mo
arXiv:2605.17033v1 Announce Type: new Abstract: Urgently needed generalizable robot object interaction and manipulation requires high-quality Cross-Category object perception. As a pioneer of this are
arXiv:2405.06415v2 Announce Type: replace-cross Abstract: While metric and similarity learning has been extensively studied from several theoretical perspectives, a rigorous understanding of its gener
arXiv:2605.18398v1 Announce Type: cross Abstract: We develop a complete theory of projective cross-ratios in n-dimensional Plane-Based Geometric Algebra (PGA), R(n,0,1), covering geometric objects of
arXiv:2605.18422v1 Announce Type: cross Abstract: The functional ANOVA, or Hoeffding decomposition, provides a principled framework for interpretability by decomposing a model prediction into main eff
arXiv:2605.16355v1 Announce Type: cross Abstract: We present Density-Sampled Gaussians (DeG), a novel 3D representation designed to bridge the gap between adaptive rendering primitives and scalable ge
arXiv:2605.16277v1 Announce Type: cross Abstract: This mid-year report summarizes teacher use of Colleague AI across 12 Washington State school districts from September 1 to December 31, 2025. Produce
arXiv:2605.18365v1 Announce Type: new Abstract: Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only impli
arXiv:2605.17354v1 Announce Type: new Abstract: Monocular 3D hand reconstruction is intrinsically a geometric problem, yet RGB appearance features alone often struggle to resolve severe ambiguities ca
arXiv:2605.18276v1 Announce Type: cross Abstract: Learning dynamical systems through operator-theoretic representations provides a powerful framework for analyzing complex dynamics, as spectral quanti
arXiv:2505.20914v2 Announce Type: replace Abstract: General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties, while simul
arXiv:2602.08206v2 Announce Type: replace Abstract: Open-vocabulary semantic segmentation has become an important direction in remote sensing, as it enables recognition beyond predefined land-cover ca
arXiv:2605.16371v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) often struggle with geometric reasoning due to visual hallucinations and a lack of mathematically precise Chain-of-Thou
arXiv:2602.23058v2 Announce Type: replace Abstract: Energy-based predictive world models provide a powerful approach for multi-step visual planning by reasoning over latent energy landscapes rather th
arXiv:2506.13189v3 Announce Type: replace-cross Abstract: Robot teleoperation via augmented reality (AR) offers a promising path toward more intuitive human-robot interaction (HRI). We present a head-
arXiv:2605.17086v1 Announce Type: cross Abstract: Automation affects the labour content of work differently across different contexts. Yet, most existing exposure measures assign fixed scores to tasks
arXiv:2605.16520v1 Announce Type: new Abstract: Sampling-based optimization (SBO), like cross-entropy method and evolutionary algorithms, has achieved many successes in solving non-convex problems wit
arXiv:2506.12648v2 Announce Type: replace-cross Abstract: Iteration complexities for optimizing smooth functions with first-order algorithms are typically stated in terms of a global Lipschitz constan
arXiv:2512.22473v5 Announce Type: replace-cross Abstract: Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale languag
arXiv:2602.07884v2 Announce Type: replace-cross Abstract: Survival analysis is complicated by censored data, high-dimensional features, and non-linear interactions. Classical models offer interpretabi
arXiv:2511.19078v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, including multi-step
arXiv:2605.17727v1 Announce Type: new Abstract: Frozen vision-language embeddings contain signals at multiple semantic resolutions, from object identity to attributes, relations, and full-caption mean
arXiv:2605.16668v1 Announce Type: cross Abstract: We introduce GraViti, a transformer-based graph-level variational autoencoder that maps entire graphs to compact latent vectors. This design produces
arXiv:2605.16714v1 Announce Type: new Abstract: Security knowledge graphs can provide computable external memory for security agents, but constructing them from long-form cyber threat intelligence (CT
arXiv:2605.18567v1 Announce Type: new Abstract: Structural equation modeling is widely used in IS research. However, inconsistent construct definitions impede the cumulative development of knowledge.
arXiv:2605.16873v1 Announce Type: new Abstract: Diffusion priors have recently demonstrated strong capability in enhancing the quality of sparse-view 3D reconstruction by augmenting training views at
arXiv:2605.16389v1 Announce Type: cross Abstract: Haptic rendering of viscoelastic materials that exhibit creep and stress relaxation is crucial for many applications, such as medical training with re
arXiv:2506.23287v3 Announce Type: replace Abstract: In single-cell research, tracing and analyzing high-throughput single-cell differentiation trajectories is crucial for understanding biological proc
On Monday, the jury in Musk v. Altman dealt Elon Musk a major blow—reaching a unanimous advisory verdict that he had sued OpenAI too late and, as a result, his claims are barred by the applicable stat
arXiv:2605.17875v1 Announce Type: new Abstract: The accurate automated diagnosis of cardiac abnormalities from 12-lead electrocardiograms (ECGs) is critical for managing cardiovascular disease. Howeve
arXiv:2605.16442v1 Announce Type: cross Abstract: Long-horizon vessel trajectory forecasting under real ocean conditions is critical for collision avoidance, traffic management, and route planning. Ho
arXiv:2605.17177v1 Announce Type: cross Abstract: Understanding the behavior of stochastic gradient methods is a central problem in modern machine learning. Recent work has highlighted diagonal linear
arXiv:2605.18408v1 Announce Type: new Abstract: Accurate vessel estimated-time-of-arrival forecasts are critical for port operations and decarbonization, yet global-scale travel-time prediction remain
arXiv:2605.17543v1 Announce Type: new Abstract: Video outpainting generates plausible visual content beyond the original spatial extent of a video, playing a key role in adapting videos to diverse dis
arXiv:2605.16953v1 Announce Type: new Abstract: While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled b
How do we design materials with AI? Excited to introduce Crys-JEPA, a new generative technique in collaboration w/ @liun_online, Kostya Novoselov, @ylecun & team. We achieved 47.9% VSUN on MP20 by bui
Physics-informed neural networks (PINNs) use specialized loss functions that combine data-fitting terms with physics constraints derived from differential equations, allowing the network to learn solu
arXiv:2603.02512v4 Announce Type: replace-cross Abstract: Human-Certified Module Repositories (HCMRs) are introduced in this work as a new architectural model for constructing trustworthy software in
arXiv:2605.17481v1 Announce Type: new Abstract: Nowadays, people in Bangladesh frequently rely on the internet and social media for daily news instead of traditional newspapers. However, the spread of
arXiv:2605.18345v1 Announce Type: cross Abstract: Hybrid quantum-classical neural networks (HQNNs) are emerging as a practical approach for quantum machine learning in the noisy intermediate-scale qua
arXiv:2605.17286v1 Announce Type: new Abstract: While hyperspectral imaging provides rich spatial-spectral information across hundreds of narrow wavelength bands for precise material identification, g
A developer created a visualization tool that displays GPT-2's internal concept activations in real-time during text generation, representing the model's 'thinking' process as a 3D graph that updates
arXiv:2605.16682v1 Announce Type: new Abstract: Identifying latent state representations and dynamics is essential when direct modeling in observation space is infeasible, particularly under partial a
arXiv:2605.17248v1 Announce Type: new Abstract: Diffusion-based extit{image-to-video} (I2V) generation has become a central direction in generative models by turning a reference image, with optional c