Knowledge catalogue
arXiv:2603.07474v2 Announce Type: replace-cross Abstract: What is the interplay between semantic representations learned by language models (LM) from surface form alone to those learned from more grou
arXiv:2604.19761v1 Announce Type: new Abstract: Modern machine learning is still largely organized around a single recipe: choose a parameterized model family and optimize its weights. Although highly
arXiv:2506.21095v4 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative training while preserving privacy, yet it introduces a critical challenge: the 'illusion of fair
Cognition AI shares insights and lessons learned from developing cloud-based AI agents, likely covering technical challenges, architectural decisions, and practical implementation strategies for build
arXiv:2510.13928v2 Announce Type: replace-cross Abstract: We propose and test the LLM Brain Rot Hypothesis: continual exposure to junk web text induces lasting cognitive decline in large language mode
arXiv:2604.19795v1 Announce Type: new Abstract: We introduce prism{} (extbf{P}robabilistic extbf{R}etrieval with extbf{I}nformation-extbf{S}tratified extbf{M}emory), an evolutionary memory substrate f
arXiv:2604.20331v1 Announce Type: cross Abstract: Large language models (LLMs), trained on vast datasets, encode extensive real-world knowledge within their parameters, yet their black-box nature obsc
arXiv:2604.17172v2 Announce Type: replace-cross Abstract: The rapid growth of large language models (LLMs) has made GPU communication a critical bottleneck. While prior work reduces communication volu
arXiv:2604.18805v1 Announce Type: new Abstract: Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously, yet whether their reasoning adheres to t
arXiv:2604.19657v1 Announce Type: cross Abstract: AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., pers
arXiv:2604.19747v1 Announce Type: new Abstract: Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing
arXiv:2604.18751v1 Announce Type: cross Abstract: Nonlinear machine-learning models are increasingly used to discover causal relationships in time-series data, yet the interpretation of their outputs
arXiv:2604.18589v1 Announce Type: cross Abstract: Thematic analysis is difficult to scale: manual workflows are labor-intensive, while fully automated pipelines often lack controllability and transpar
Last year at Google Cloud Next ‘25, we asked you to imagine a new future for AI. At Next ‘26, the question before you is how do you move AI into production across your entire enterprise? According to
We are officially moving past the era of one-size-fits-all AI. Enterprises today require highly specialized, role-specific tools to drive real productivity — but they cannot afford to sacrifice securi
arXiv:2604.18644v1 Announce Type: cross Abstract: Predictive policing systems that allocate patrol resources based solely on predicted crime risk can unintentionally amplify racial disparities through
arXiv:2604.19457v1 Announce Type: new Abstract: Long-horizon enterprise agents make high-stakes decisions (loan underwriting, claims adjudication, clinical review, prior authorization) under lossy mem
arXiv:2604.19149v1 Announce Type: cross Abstract: Thinking LLMs produce reasoning traces before answering. Prior activation steering work mainly targets on shaping these traces. It remains less unders
arXiv:2604.19538v1 Announce Type: new Abstract: Agentic AI, with goal-directed, proactive, and autonomous decision-making capabilities, offers a compelling opportunity to address movement-related risk
arXiv:2604.19117v1 Announce Type: new Abstract: When a language model agrees with a user's false belief, is it failing to detect the error, or noticing and agreeing anyway? We show the latter. Across
arXiv:2601.03442v4 Announce Type: replace-cross Abstract: Inspired by the success of performing multiple local optimization steps between communication rounds in federated learning, incorporating such
arXiv:2604.19631v1 Announce Type: new Abstract: Dynamic Scene Graph Generation (DSGG) aims to structurally model objects and their dynamic interactions in video sequences for high-level semantic under
arXiv:2604.19093v1 Announce Type: cross Abstract: Multi-modal test-time adaptation (TTA) enhances the resilience of benchmark multi-modal models against distribution shifts by leveraging the unlabeled
arXiv:2604.18649v1 Announce Type: cross Abstract: As generative AI faces intensifying legal challenges, the machine learning community has increasingly relied on post-hoc mitigation -- especially mach
arXiv:2510.16822v3 Announce Type: replace-cross Abstract: Coral reefs are rapidly declining under anthropogenic pressures (e.g., climate change), creating an urgent need for scalable and automated mon
arXiv:2604.19049v1 Announce Type: cross Abstract: LLM-assisted defect discovery has a precision crisis: plausible-but-wrong reports overwhelm maintainers and degrade credibility for real findings. We
arXiv:2604.19092v1 Announce Type: cross Abstract: Recent advances in large-scale video world models have enabled increasingly realistic future prediction, raising the prospect of leveraging imagined v
At Google Cloud Next, we are announcing innovations across every layer of our storage stacks — performance, intelligence, and management — to ensure your data is as fast and as useful as the AI models
Companies are shifting from gen AI that simply answers questions to autonomous agents that perceive, reason, and act on their behalf. Attempting to scale these agents on legacy stacks exposes structur
arXiv:2604.16482v1 Announce Type: new Abstract: As vision-based robots navigate larger environments, their spatial memory grows without bound, eventually exhausting computational resources, particular
arXiv:2601.13099v2 Announce Type: replace Abstract: Arabic is a highly diglossic language where most daily communication occurs in regional dialects rather than Modern Standard Arabic (MSA). Despite t
arXiv:2602.11161v2 Announce Type: replace-cross Abstract: The web's information ecosystem demands fact-checking systems that are both scalable and epistemically trustworthy. Automated approaches offer
arXiv:2602.06221v2 Announce Type: replace Abstract: Multiple-choice question answering (MCQA) is standard in NLP, but benchmarks lack rigorous quality control. We present BenchMarker, an education-ins
arXiv:2511.03180v2 Announce Type: replace Abstract: As multilingual Large Language Models (LLMs) gain traction across South Asia, their alignment with local ethical norms, particularly for Bengali, sp
arXiv:2604.18423v1 Announce Type: new Abstract: India's linguistic landscape, spanning 22 scheduled languages and hundreds of marginalized dialects, has driven rapid growth in NLP datasets, benchmarks
arXiv:2604.16989v1 Announce Type: new Abstract: We report new results on six problems in mathematics and theoretical computer science, produced with the assistance of Bolzano, an open-source multi-age
arXiv:2604.16331v1 Announce Type: cross Abstract: Embodied task planning requires agents to execute long-horizon, goal-directed actions in complex 3D environments, where success depends on both immedi
arXiv:2604.17208v1 Announce Type: new Abstract: Digital subtraction angiography (DSA) in coronary imaging is fundamentally challenged by physiological motion, forcing reliance on raw angiograms clutte
arXiv:2509.00789v2 Announce Type: replace Abstract: The pursuit of autonomous agents capable of temporally coherent planning is hindered by a fundamental flaw in current vision-language models (VLMs):
arXiv:2603.07084v2 Announce Type: replace-cross Abstract: Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely m
arXiv:2604.17177v1 Announce Type: new Abstract: Fine-tuning adapts pretrained networks to new objectives. Whether the resulting depth profile of representational change reflects an intrinsic property
arXiv:2604.16656v1 Announce Type: new Abstract: All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latenc
arXiv:2604.18167v1 Announce Type: new Abstract: Modern text-to-image (T2I) models amplify harmful societal biases, challenging their ethical deployment. We introduce an inference-time method that reli
arXiv:2602.07794v3 Announce Type: replace Abstract: Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual r
arXiv:2604.18379v1 Announce Type: new Abstract: Most data-driven ionospheric forecasting models operate on gridded products, which do not preserve the time-varying sampling structure of satellite-base
arXiv:2604.16685v1 Announce Type: new Abstract: Accurate prediction of cancer progression remains a challenge due to the high heterogeneity of molecular omics data across patients. While biologically
arXiv:2604.17283v1 Announce Type: new Abstract: User preferences evolve across months of interaction, and tracking them requires inferring when a stated preference has been changed by a subsequent lif
arXiv:2408.09049v3 Announce Type: replace Abstract: Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs. A popular strategy i
arXiv:2604.17115v1 Announce Type: new Abstract: Interactive video segmentation models such as SAM2 have demonstrated strong generalization across diverse visual domains. However, under weak user super
arXiv:2604.17651v1 Announce Type: new Abstract: World models, generative AI systems that simulate how environments evolve, are transforming autonomous driving, yet all existing approaches adopt an ego
arXiv:2604.18225v1 Announce Type: new Abstract: Is Segment Anything Model 3 (SAM3) capable in segmenting Any Pathology Images? Digital pathology segmentation spans tissue-level and nuclei-level scales
arXiv:2410.21160v2 Announce Type: replace-cross Abstract: Background and Objective: In the realm of ophthalmic imaging, accurate vascular segmentation is paramount for diagnosing and managing various
arXiv:2604.16763v1 Announce Type: new Abstract: Causal inference from electronic health records (EHR) is fundamentally limited by unmeasured confounding: critical clinical states such as frailty, goal
arXiv:2601.06931v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly deployed in socially consequential settings, raising concerns about social bias driven by demog
arXiv:2604.16417v1 Announce Type: cross Abstract: This study examines the relationship between media coverage and public information demand during the Lebanon conflict in March 2026. Using a dataset o
arXiv:2510.12831v3 Announce Type: replace Abstract: Multi-turn Text-to-SQL aims to translate a user's conversational utterances into executable SQL while preserving dialogue coherence and grounding to
arXiv:2511.03855v2 Announce Type: replace Abstract: Deep learned (DL) models for image recognition have been shown to fail to generalize to data from different devices, populations, etc. COVID-19 dete
arXiv:2604.16428v1 Announce Type: new Abstract: Time series foundation models (TSFMs) are widely used as generic feature extractors, yet the notion of non-stationarity in their embedding spaces remain
arXiv:2604.00131v2 Announce Type: replace Abstract: Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual
arXiv:2604.18450v1 Announce Type: cross Abstract: Empirical studies of trained models often report a transient regime in which signal is detectable in a finite gradient descent time window before over