Knowledge catalogue
As models become more capable, the risks associated with developing and testing them internally also grow. We temporarily paused reinforcement learning (RL) training on our latest models intended for
arXiv:2601.10161v3 Announce Type: replace-cross Abstract: Named Entity Recognition (NER) and Personally Identifiable Information (PII) anonymization are critical tasks in Natural Language Processing (
arXiv:2608.15373v1 Announce Type: new Abstract: Inverse physics-informed neural networks (PINNs) can reconstruct a field accurately while returning an incorrect physical parameter. We introduce a two-
arXiv:2608.16756v1 Announce Type: new Abstract: RAW video restoration is fundamental to high-quality low-level perception and serves as the basis for a wide range of downstream vision applications. Wh
For financial institutions, operational resilience has long been embedded in regulatory and supervisory expectations — to say nothing of the high expectations of consumers. With the implementation of
arXiv:2608.15407v1 Announce Type: cross Abstract: An invariant behavioral profile is the defining vulnerability of traditional honeypot installations: a skilled adversary can confirm the presence of a
arXiv:2608.16666v1 Announce Type: new Abstract: This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcook
arXiv:2608.15972v1 Announce Type: cross Abstract: Synchronized camera and wireless measurements observe the same scene through different physical channels. The central difficulty is that a representat
arXiv:2511.11427v2 Announce Type: replace Abstract: Referring Expression Comprehension (REC) requires models to localize objects in images based on different types of natural language descriptions. Ev
arXiv:2608.16210v1 Announce Type: new Abstract: Aggregate accuracy hides where models succeed and fail. Estimating conditional performance profiles from gold labels alone is expensive, while cheap aux
arXiv:2608.14763v1 Announce Type: cross Abstract: Assessment of ventriculomegaly (VM) on fetal brain ultrasound relies primarily on measuring lateral ventricular atrial width on standard planes, which
arXiv:2608.15877v1 Announce Type: new Abstract: Search and recommendation serve a shared discovery objective but encode intent differently. We study this boundary through Dear Algo on Threads, a deplo
arXiv:2608.15256v1 Announce Type: new Abstract: Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL). However, pushing
arXiv:2608.16274v1 Announce Type: cross Abstract: Positional encoding is a fundamental component of Transformer-based generative recommendation models, where user histories are modeled as autoregressi
arXiv:2608.14935v1 Announce Type: cross Abstract: Turbulent fluxes between the surface and the atmosphere are typically parameterized using empirically fit relationships. Here we test machine learning
arXiv:2505.14107v5 Announce Type: replace-cross Abstract: The emergence of groundbreaking large language models capable of performing complex reasoning tasks holds significant promise for addressing v
arXiv:2608.14637v1 Announce Type: new Abstract: Long-duration stationary energy storage requires batteries whose degradation can be detected before substantial capacity loss has accumulated. Iron-chro
arXiv:2608.15502v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising foundation for Embodied AI, but their high inference cost poses significant challenges f
arXiv:2608.14651v1 Announce Type: new Abstract: Effective disaster risk communication is a foundational humanitarian challenge, yet current emergency infrastructure fails to meet the needs of individu
arXiv:2608.14952v1 Announce Type: cross Abstract: A structured world-state (entities, relations, context, and predictive cues) is designed to preserve prediction-critical content when perception degra
arXiv:2608.14603v1 Announce Type: cross Abstract: Cooperative perception enables vehicles and infrastructure to exchange sensor data via Vehicle-to-Everything (V2X) communication, extending sensing co
arXiv:2608.15177v1 Announce Type: cross Abstract: The increasing complexity of digital financial systems has reshaped financial fraud detection from isolated transaction classification into relational
arXiv:2608.15602v1 Announce Type: cross Abstract: While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlo
arXiv:2608.15065v1 Announce Type: new Abstract: Large Reasoning Models produce diverse, sometimes inconsistent answers across repeated queries on the same problem, so multi-sample inference is a prere
arXiv:2608.15084v1 Announce Type: cross Abstract: Test-time augmentation (TTA) has proven effective for improving model robustness and uncertainty estimation in computer vision, yet its application to
arXiv:2507.19894v2 Announce Type: replace Abstract: With the rapid advancement of generative models, privacy, copyright, safety, and reliability risks have attracted growing attention. To mitigate the
arXiv:2608.16824v1 Announce Type: new Abstract: Generative Engine Optimization (GEO) modifies web content to increase its likelihood of being selected and cited by generative search engines. This can
GLM-5.3 achieves 60 on the Artificial Analysis Intelligence Index, on par with Kimi K3 and up 7 points from GLM-5.2. Once the weights are released it will be tied as the leading open weights model @Za
arXiv:2607.18483v2 Announce Type: replace-cross Abstract: The digital substrate - data, algorithms, infrastructure, platforms, applications - is being governed without adequate conceptual foundations.
arXiv:2608.16494v1 Announce Type: cross Abstract: Modern power systems face growing operational complexity driven by the integration of renewable energy sources, decentralization, and the need for rea
arXiv:2608.15520v1 Announce Type: new Abstract: A multimodal system may begin inference holding only some of its inputs and may acquire the rest at a cost. With adaptive acquisition, the policy determ
arXiv:2608.16837v1 Announce Type: cross Abstract: Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation mo
arXiv:2608.16353v1 Announce Type: cross Abstract: Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stak
arXiv:2503.07825v3 Announce Type: replace-cross Abstract: We present an advance in wearable technology: a mobile-optimized, real-time, ultra-low-power event camera system that enables natural hand ges
arXiv:2504.20823v3 Announce Type: replace Abstract: Accurate remaining useful life (RUL) estimation underpins safe operation and cost-effective maintenance of aerospace propulsion systems. We propose
arXiv:2608.16763v1 Announce Type: new Abstract: Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency,
arXiv:2608.15317v1 Announce Type: new Abstract: Scene coordinate regression (SCR) achieves strong performance in outdoor LiDAR localization, but it usually requires scene-specific training that can ta
arXiv:2608.14727v1 Announce Type: new Abstract: Fabric inspection in the garment industries of low-income economies remains largely manual, and commercial vision systems are priced beyond most small a
arXiv:2608.15760v1 Announce Type: cross Abstract: Decoding is an essential component of quantum error correction (QEC), translating stabilizer measurement outcomes into corrective actions that suppres
arXiv:2608.15299v1 Announce Type: cross Abstract: Sparsely-activated Mixture-of-Experts (MoE) Transformers universally fix the same number of routed experts across all layers, a convention that ignore
arXiv:2608.15277v1 Announce Type: new Abstract: Greedy sampling produces a compact yet representative summary of normal data, which is essential for reliable anomaly detection that relies on measuring
arXiv:2608.15437v1 Announce Type: cross Abstract: Multimodal bird's-eye-view (BEV) perception combines LiDAR depth accuracy with dense camera semantics, but its high computational cost and imperfect s
arXiv:2608.15956v1 Announce Type: new Abstract: Agentic retrieval workflows produce query, retrieval, and stopping traces as a byproduct of answering questions. We study how these traces can adapt a d
The rise of neoclouds — AI-first cloud providers — is transforming enterprise infrastructure. The unique requirements of AI models and agents have paved the way for new collaborations between hardware
arXiv:2608.16104v1 Announce Type: new Abstract: Diffusion and flow matching models have made significant progress in text-to-image generation, yet high computation, quadratic complexity, and large mem
arXiv:2608.15919v1 Announce Type: cross Abstract: Retrieval-Augmented Generation over knowledge graphs (Graph-RAG) has emerged as a powerful paradigm for grounding large language models in domain-spec
arXiv:2608.15573v1 Announce Type: new Abstract: Reliable long-horizon planning remains a key challenge in end-to-end autonomous driving. By accounting for future motion evolution and potential consequ
arXiv:2512.03444v2 Announce Type: replace Abstract: Deep learning methods have significantly enhanced motion planning for robotic manipulators by leveraging prior experiences within planning datasets.
arXiv:2608.16198v1 Announce Type: cross Abstract: Dermatology models face distribution shifts in teledermatology settings, where submitted images differ from the training data in lighting, angle, dist
arXiv:2608.14568v1 Announce Type: new Abstract: As Artificial Intelligence (AI) systems become deeply integrated into critical global infrastructure, the urgency for robust governance frameworks has i
arXiv:2608.15362v1 Announce Type: cross Abstract: We propose a methodology based on the standard ReLU Deep Neural Networks (DNN) to make predictions and quantify their uncertainty. Classically, people
arXiv:2608.15924v1 Announce Type: new Abstract: Cloud-side inference gives imitation-learning policies access to greater computational resources, but communication and computation delays can degrade c
arXiv:2608.16195v1 Announce Type: new Abstract: Achieving human-level competitive intelligence and physical agility in humanoid robots remains a profound challenge, particularly in contact-rich and hi
arXiv:2608.16433v1 Announce Type: new Abstract: Traversal Risk Graphs (TRGs) provide a compact, terrain-aware representation for global navigation, but native TRG costs are computed over circular node
arXiv:2608.15621v1 Announce Type: new Abstract: Human Activity Recognition (HAR) with self-administered wearables, such as at-home rehabilitation and exercise monitoring, often requires reattaching in
arXiv:2608.15043v1 Announce Type: new Abstract: Video world models are increasingly used as simulators for planning and embodied decision making, yet improving them at inference time introduces a subt
arXiv:2608.15217v1 Announce Type: new Abstract: Existing blind image quality assessment (BIQA) methods typically rely on synthetic distortions and subjective annotations, limiting generalization in re
arXiv:2608.15295v1 Announce Type: new Abstract: Foundation segmentation models excel at generating high-quality, class-agnostic masks, but they struggle to associate these proposals with specific targ
arXiv:2608.16320v1 Announce Type: new Abstract: Streaming video understanding demands direct responses from the causally observed prefix of an unfolding video. Existing systems add inference-time memo
arXiv:2608.15224v1 Announce Type: new Abstract: Reliable post-hoc evaluation asks whether already generated text satisfies a target criterion after generation. In this paper we study a focused frozen-