Knowledge catalogue
arXiv:2608.01704v1 Announce Type: cross Abstract: A benchmark score means nothing without knowing what a trivial method achieves and what the best possible method could achieve. We construct both boun
arXiv:2608.00635v1 Announce Type: new Abstract: We present FlowPilot, a compact world-action model for real-time onboard UAV navigation from depth. Unlike map-then-optimize pipelines that require loca
arXiv:2608.02433v1 Announce Type: new Abstract: Reinforcement learning and control theory are two adjacent scientific fields that focus on optimizing the controller of unknown dynamical systems using
arXiv:2608.00726v1 Announce Type: new Abstract: Frozen vision foundation models are commonly evaluated through a single global image embedding, but this interface can conflate missing information with
arXiv:2608.01950v1 Announce Type: new Abstract: Autonomous 3D reconstruction with depth sensors is strongly affected by reflective surfaces, which cause missing or unreliable measurements and reduce t
arXiv:2608.00695v1 Announce Type: new Abstract: Zero-shot anomaly detection (ZSAD) aims to detect anomalies and localize defective regions in unseen target domains without target training data. Recent
arXiv:2608.00970v1 Announce Type: new Abstract: Object-oriented aerial vision-and-language navigation (VLN) requires searching for a described target and landing on it precisely, under long-horizon an
arXiv:2603.12828v2 Announce Type: replace-cross Abstract: This paper addresses a missing capability in infrastructure resilience: turning fast, global AI weather forecasts into asset-scale, actionable
arXiv:2608.02123v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference only when drafted continuations survive target-model verification. Semi-autoregressive drafters such as D
arXiv:2608.00484v1 Announce Type: cross Abstract: Soft robotic substrates are promising for Physical Reservoir Computing (PRC) because their compliant nonlinear dynamics can provide temporal memory, h
arXiv:2607.09842v2 Announce Type: replace-cross Abstract: We investigate whether identity-specifying system prompts produce statistically distinguishable geometric fingerprints in the hidden-state tra
arXiv:2608.00613v1 Announce Type: new Abstract: Physical-world interaction is inherently dynamic, as environments can evolve during execution, requiring agents to adapt their plans under non-stationar
arXiv:2608.00608v1 Announce Type: new Abstract: Visible and near-infrared (vis-NIR) and mid-infrared (MIR) spectroscopy enable rapid, cost-effective prediction of soil properties. Yet, translating hig
arXiv:2608.01230v1 Announce Type: new Abstract: Indonesia's relocation of its political and administrative capital from Jakarta to Ibu Kota Nusantara (IKN) has been framed around a ``Forest City'' vis
arXiv:2608.02402v1 Announce Type: new Abstract: Thermochemical upgrading of plastic waste is a key upcycling pathway, yet the experimental literature is fragmented by heterogeneous conditions and inco
arXiv:2507.21449v2 Announce Type: replace-cross Abstract: Degeneracy is an inherent feature of the loss landscape of neural networks, but it is not well understood how stochastic gradient MCMC (SGMCMC
arXiv:2608.02100v1 Announce Type: cross Abstract: As AI increasingly participates in human decision making, understanding how decision-making authority is distributed between humans and AI has become
arXiv:2608.01104v1 Announce Type: new Abstract: Whole slide image (WSI) classification is an evidence-driven task, where diagnostic cues are often sparse, spatially organized, and class-dependent. Exi
arXiv:2608.00084v1 Announce Type: new Abstract: We present PixCell, a neurosymbolic system in which multimodal agents convert a visually presented photonic component into a parametric program over a s
arXiv:2602.10719v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) driving augments end-to-end (E2E) planning with language-enabled visual backbones, yet it remains unclear how vis
arXiv:2603.28067v2 Announce Type: replace Abstract: Digital testing has emerged as a key paradigm for the development and verification of autonomous maritime navigation systems, yet the availability o
arXiv:2603.03320v2 Announce Type: replace Abstract: Effective communication often relies on aligning a message with an audience's narrative and worldview. Narrative shift involves transforming text to
arXiv:2608.01202v1 Announce Type: new Abstract: Fruit ripeness prediction (FRP) is a classification-based agricultural computer vision task that has attracted much attention, thanks to its wide-rangin
arXiv:2608.01007v1 Announce Type: new Abstract: Dual-target drug design aims to generate 3D molecules that can simultaneously interact with two target proteins, offering a promising route for discover
arXiv:2606.17020v2 Announce Type: replace Abstract: Remote sensing vision-language models have advanced Earth observation, but available large-scale vision-language resources remain RGB-centered, leav
Editor's Note: Our Future Mode series will give businesses insight into how Chrome Enterprise is approaching AI in the browser. Stay tuned for more blogs in this series.Future Mode Part 2: The foundat
arXiv:2608.01726v1 Announce Type: new Abstract: 3D Gaussian Splatting has achieved remarkable success in photorealistic and efficient rendering, leading to a rapid increase in 3D assets represented by
arXiv:2608.00932v1 Announce Type: new Abstract: The integration of artificial intelligence into medical question-answering systems has advanced rapidly; however, research remains predominantly focused
arXiv:2603.18540v2 Announce Type: replace Abstract: The increasing complexity of neural networks poses significant challenges for democratizing federated learning (FL) on resource-constrained edge dev
arXiv:2608.01492v1 Announce Type: new Abstract: Selecting a complete 3D object from a reconstructed scene with minimal user effort is essential for practical scene editing and embodied interaction. Ex
arXiv:2608.02378v1 Announce Type: new Abstract: Private inference protects both user inputs and server models during neural network inference, but existing solutions remain too slow for practical depl
arXiv:2608.00829v1 Announce Type: new Abstract: We present an autonomous robotic portrait-generation system combining real-time face detection, AI-based sketch generation, and robotic drawing. The sys
arXiv:2608.01552v1 Announce Type: cross Abstract: Quadratic Gradient (QG) is a Newton-type optimization framework that bridges first-order gradient descent and second-order optimization by incorporati
NVIDIA Alpamayo 2 Super is a publicly available 34‑billion‑parameter vision–language–action model that merges a 32‑B Cosmos 3 Super Reasoner with a 2‑B action‑expert diffusion network. It produces uni
arXiv:2608.00716v1 Announce Type: new Abstract: Robust detection of generated images is critical to counter the misuse of generative models. Existing methods primarily depend on learning from human-an
arXiv:2608.01686v1 Announce Type: new Abstract: In recent years, generative AI has attracted significant public attention, and its use has been rapidly expanding across a wide range of domains. From c
arXiv:2608.01677v1 Announce Type: new Abstract: Myocardial strain analysis of cardiac magnetic resonance (CMR) images provides an important tool for evaluating cardiac function. However, current techn
arXiv:2608.00156v1 Announce Type: cross Abstract: The push for broader coverage in future cellular networks depends on reliable service, yet this is increasingly harder to do as we encounter more inst
arXiv:2608.00776v1 Announce Type: new Abstract: Traditional reaction yield prediction is constrained by 1D quantum descriptors that lack explicit spatial information. To address this gap, a dual-modal
arXiv:2608.02236v1 Announce Type: new Abstract: Zero-shot skeleton-based action recognition (ZSAR) aims to recognize unseen action categories by aligning skeleton features with textual semantics. Howe
arXiv:2608.01410v1 Announce Type: cross Abstract: General-purpose humanoid trackers can execute diverse references, but their zero-shot coverage depends on large embodied corpora that are costly to ex
arXiv:2608.00877v1 Announce Type: new Abstract: Remote-sensing multimodal large language models (MLLMs) often assert facts that imagery cannot establish, such as a facility's identity or function. Coo
arXiv:2608.01896v1 Announce Type: new Abstract: Existing generative models for earth observation (EO) predominantly rely on fine-tuning natural image priors, which limits their scalability and introdu
arXiv:2608.02315v1 Announce Type: new Abstract: Geospatial foundation models aim to learn representations that transfer across regions and sensors, yet evaluating them on specific tasks requires large
arXiv:2602.01893v2 Announce Type: replace-cross Abstract: We present a geometric framework for analysing multi-head attention in large language models (LLMs). Without altering the mechanism, we view s
arXiv:2603.07564v2 Announce Type: replace Abstract: Satellite video object tracking (SVOT) remains fundamentally challenging due to texture scarcity, arbitrary rotation, aspect ratio changes, and seve
arXiv:2608.00663v1 Announce Type: new Abstract: Audio-driven emotional talking face generation aims to synthesize realistic videos with expressive facial dynamics. However, existing methods struggle t
arXiv:2608.02064v1 Announce Type: cross Abstract: Feed-forward networks (FFNs) account for a large fraction of Transformer parameters, yet their hidden width is usually constant across depth. We ask w
arXiv:2608.02068v1 Announce Type: new Abstract: Monocular depth foundation models, benefiting from large-scale synthetic training data, have demonstrated strong generalization. However, they often hal
arXiv:2603.23179v2 Announce Type: replace Abstract: Diffusion models provide powerful priors for 2D image completion, but these priors are learned on bounded planar images and do not transfer directly
I would love some feedback on this work in progress. Create, dialog with, mash up, and evolve spirit guides based on real concepts spanning psychological, philosophical, and religious origins. Honestl
Given today, it is surprising how daring Microsoft & Google were initially with AI. Microsoft released GPT-4 before OpenAI, didn't back down after Sydney & got Copilot to market quickly (the 1st profe
arXiv:2608.02366v1 Announce Type: new Abstract: Multivariate time series imputation is fundamental to downstream analysis, yet modeling inter-variable dependencies with incomplete observations remains
arXiv:2608.02353v1 Announce Type: new Abstract: Recent advances in agentic workflow optimization automate workflow design through task-specific workflow search or input-conditioned architecture select
arXiv:2608.02322v1 Announce Type: new Abstract: Accurate and efficient reconstruction of cloud-contaminated and noise-corrupted NDVI time series remains a challenge in remote sensing. Deep learning pr
arXiv:2509.22910v2 Announce Type: replace Abstract: Given that Visual SLAM relies on appearance cues for localization and scene understanding, texture-less or visually degraded environments (e.g., pla
arXiv:2603.13418v2 Announce Type: replace Abstract: Structured pruning is widely applied to compress large language models (LLMs), but its performance depends heavily on how neuron importance is estim
It is one of the best local models ever released, in both 20B and 120B versions. I always come back to it, especially the 120B version. Its only competition is, in my opinion, Qwen 3.5 122B, but that
arXiv:2608.02585v1 Announce Type: cross Abstract: Optimization-based latent reasoning improves large language model outputs by optimizing instance-specific continuous states at test time while keeping
arXiv:2608.01528v1 Announce Type: new Abstract: Vector symbolic architectures (VSA) are widely used for reasoning in neuro-symbolic (NeSy) AI, yet high-dimensional codebooks often create severe memory