Knowledge catalogue
If anyone thought artificial intelligence was running into a slow patch, let alone running into any fundamental technical or financial hurdles, this week quieted the doubters — at least for now. In a
arXiv:2604.27394v1 Announce Type: cross Abstract: Conditional Average Treatment Effect (CATE) estimation in practice demands three properties simultaneously: heterogeneous effects au(x), calibrated un
arXiv:2504.12612v2 Announce Type: replace Abstract: Provenance is the chronological history of things, resonating with the fundamental pursuit to uncover origins, trace connections, and situate entiti
arXiv:2604.27092v1 Announce Type: new Abstract: Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods
I have been testing DeepSeek-V4-Pro with the Pi coding agent. I am mindblown by how well it works out of the box. A few notes: I spent a few hours building an LLM wiki with an agent powered entirely b
arXiv:2603.20965v2 Announce Type: replace-cross Abstract: This paper studies whether a lightweight supervised aggregator can combine diverse zero-shot large language model outputs into a stronger down
arXiv:2604.27063v1 Announce Type: new Abstract: Continual learning agents with finite capacity must balance acquiring new knowledge with retaining the old. This requires controlled forgetting of knowl
arXiv:2604.27289v1 Announce Type: new Abstract: We present five results in the theory of structural governance for cognitive workflow systems. Three are mechanized in Coq 8.19 using the Interaction Tr
arXiv:2604.27859v1 Announce Type: new Abstract: Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined env
arXiv:2604.27358v1 Announce Type: new Abstract: As large language model (LLM) agents are deployed in high-stakes environments, the question of how safely to delegate subtasks to specialized sub-agents
arXiv:2604.28087v1 Announce Type: cross Abstract: Rule-based systems remain central in safety-critical domains but often struggle with scalability, brittleness, and goal misspecification. These limita
arXiv:2601.15808v2 Announce Type: replace Abstract: Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving. While the majority of existing ef
arXiv:2604.26283v1 Announce Type: cross Abstract: High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during
arXiv:2604.26211v1 Announce Type: new Abstract: In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that
arXiv:2604.26508v1 Announce Type: cross Abstract: Deploying Vision-Language Models (VLMs) on edge devices remains challenging due to their substantial computational and memory demands, which exceed th
arXiv:2604.25057v1 Announce Type: new Abstract: Understanding the geographic reach and community structure of one's scholarly citations is increasingly valuable for career development, grant applicati
arXiv:2604.25782v1 Announce Type: cross Abstract: Earth observation satellite imaging scheduling is a challenging NP-hard combinatorial optimisation problem central to space mission operations. While
arXiv:2604.25670v1 Announce Type: new Abstract: Reliable estimation of neuromuscular activation is a key enabler for adaptive and personalized control in wearable robotics. However, surface electromyo
arXiv:2409.13869v2 Announce Type: replace-cross Abstract: In this study, I investigate how generative artificial intelligence (AI) systems reproduce and reinforce societal biases, with a specific focu
arXiv:2512.20677v4 Announce Type: replace-cross Abstract: The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically eval
arXiv:2604.25665v1 Announce Type: new Abstract: Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document
arXiv:2604.25130v1 Announce Type: new Abstract: Evaluating long document summaries remains the primary bottleneck in summarization research. Existing metrics correlate weakly with human judgments and
arXiv:2604.22864v1 Announce Type: cross Abstract: Existing benchmarks for systematic reviewing remain limited either in scale or in disciplinary coverage, with some collections comprising only a modes
arXiv:2604.24648v1 Announce Type: new Abstract: Climate change and resource depletion demand a shift from the dominant linear 'take-make-use-dispose' paradigm of construction toward circular, low-wast
arXiv:2510.10930v2 Announce Type: replace-cross Abstract: Reasoning is not just about solving problems -- it is also about evaluating which problems are worth solving at all. Evaluations of artificial
arXiv:2604.23903v1 Announce Type: cross Abstract: Large-scale neuroscience is generating rich datasets across animals, brain areas and behavioral contexts, yet our modeling efforts remains fragmented
arXiv:2604.23178v1 Announce Type: new Abstract: LLM-as-a-Judge has become the dominant paradigm for evaluating language model outputs, yet LLM judges exhibit systematic biases that compromise evaluati
arXiv:2604.24293v1 Announce Type: cross Abstract: Graph neural ordinary differential equations (Graph ODEs) extend graph learning from discrete message-passing layers to continuous-time representation
arXiv:2604.23272v1 Announce Type: new Abstract: Humans understand and interact with the real world by relying on diverse physical feedback beyond visual perception. Motivated by this, recent approache
arXiv:2604.24708v1 Announce Type: cross Abstract: Training large neural networks with data-parallel stochastic gradient descent allocates N GPU replicas to compute effectively identical updates -- a p
arXiv:2604.22892v1 Announce Type: new Abstract: Feature selection in high-dimensional genomic data (d gg n) demands methods that are simultaneously accurate, sparse, and stable. Existing approaches ei
Boaz Sobrado / Forbes: A profile of Anthony Fujiwara, who industrialized “clipping” for social media video marketing and has contributed to the rise of crypto casinos like Stake — Anthony Fujiwara is
The cost to build natural gas power plants has spiked 66% in the last two years, with prices rising from less than 1,500 per kilowatt in 2023 to 2,157 in 2025 , driven by surging demand from data cent
arXiv:2604.22189v1 Announce Type: new Abstract: This letter presents an energy-efficient multi-robot coverage path planning (MRCPP) framework for large, nonconvex Regions of Interest (ROI) containing
arXiv:2604.21982v1 Announce Type: new Abstract: Solar panels are increasingly deployed in cities on rooftops, walls, and urban infrastructure. Although the panel costs have fallen in recent years, the
arXiv:2604.22018v1 Announce Type: cross Abstract: Several brain foundation models (FM) have recently been proposed to predict brain disorders by modelling dynamic functional connectivity (FC). While t
Introducing our new work: “Learning to Orchestrate Agents in Natural Language with the Conductor” accepted at #ICLR2026 https://arxiv.org/abs/2512.04388 What if we trained an AI not to solve problems
arXiv:2604.22118v1 Announce Type: new Abstract: Optical motion capture (mocap) systems are widely used for ground-truth capture in AR/VR, SLAM and robotics datasets. These datasets require extrinsic c
Samuel Stolton / Bloomberg: The EU unveils new proposals under the DMA aimed at opening up Android to rivals' AI services; Google says the measures are “unwarranted intervention” — Google was targeted
Russell Contreras / Axios: How the Vatican is moving faster than most legacy institutions to shape AI rules and guardrails, with an AI framework, banning use of AI to write homilies, more — The Vatica
Sasha Rogelberg / Fortune: Survey of 1,050 Australian teens: ~60% said they retained access to social media accounts after ban; two-thirds say platforms took no action to remove accounts — If teenager
arXiv:2604.21276v1 Announce Type: cross Abstract: As pretrained large language models replace task-specific decoders in speech recognition, a critical question arises: do their text-derived priors mak
arXiv:2604.21420v1 Announce Type: new Abstract: Quality Estimation (QE) aims to assess machine translation quality without reference translations, but recent studies have shown that existing QE models
arXiv:2604.21793v1 Announce Type: new Abstract: In this paper, we develop a novel logic-based approach to detecting high-level temporally extended events from timestamped data and background knowledge
arXiv:2502.20769v3 Announce Type: replace Abstract: Developing interpretable models for neurodevelopmental disorders (NDDs) diagnosis presents significant challenges in effectively encoding, decoding,
arXiv:2604.21916v1 Announce Type: new Abstract: As frontier language models attain near-ceiling performance on static mathematical benchmarks, existing evaluations are increasingly unable to different
Terje Solsvik / Reuters: Norway plans to ban children from using social media until they turn 16; the government says it will introduce a bill in parliament by the end of 2026 — Norway said on Friday
arXiv:2310.02635v5 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is a promising approach for solving robotic manipulation tasks. However, it is challenging to apply the RL algorit
@themidasproj: The Wire by Acutus, an AI-generated site with articles attacking AI industry critics, appears to be funded by the OpenAI-backed super PAC Leading The Future — The reporters at this news
arXiv:2604.21860v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This pape
Ben Bergman / Business Insider: Anthropic's valuation has hit 1T on Forge Global, a leading private marketplace exchange, surpassing OpenAI's valuation on the platform of 880B — - Anthropic's valuatio
arXiv:2604.20704v1 Announce Type: cross Abstract: Adversarial robustness evaluation underpins every claim of trustworthy ML deployment, yet the field suffers from fragmented protocols and undetected g
arXiv:2603.17478v2 Announce Type: replace-cross Abstract: This study explores the combination of automated machine learning (AutoML) with model-based deep unfolding (DU) for optimizing wireless beamfo
arXiv:2601.14295v3 Announce Type: replace Abstract: Large language models increasingly function as artificial reasoners: they evaluate arguments, assign credibility, and express confidence. Yet their
Evals ~= Environments…they’re one of the best investments a team can make for improving agents Step 0: Turn On Tracing for Agents Step 1: Point compute at Traces to understand agent behavior, segment
arXiv:2604.20714v1 Announce Type: new Abstract: Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of 'Agent Engineering.' Existing automatic optimization methods
arXiv:2604.20000v1 Announce Type: new Abstract: Automated wildlife monitoring from aerial imagery is vital for conservation but remains limited by two persistent challenges: the difficulty of detectin
arXiv:2604.20147v1 Announce Type: cross Abstract: Data-driven decision-making under uncertainty typically presumes the collection of historical data from an unknown target probability distribution. Ho
Jagmeet Singh / TechCrunch: Sensor Tower: India's mobile app IAP revenue crossed 300M in Q1, up 33% YoY, with non-gaming apps generating 200M+, much of it captured by global platforms — India's mobile
Connor Stringer / Telegraph: Trump threatens to “put a big tariff on the UK” if it does not drop its digital services tax, which he views as unfairly targeting US tech companies — President tells The