Knowledge catalogue
arXiv:2605.24647v1 Announce Type: new Abstract: Personalized dialogue requires more than recalling explicit user histories: systems also need to infer hidden user states that evolve through interactio
arXiv:2605.22093v2 Announce Type: replace Abstract: Knowledge graphs have become the primary vehicle for data integration and are critical to the success of modern AI, but the diversity of KG modellin
arXiv:2605.26040v1 Announce Type: new Abstract: Graph fraud detection has long depended on Graph Neural Networks (GNNs) to propagate and aggregate information across relational data. A critical obstac
arXiv:2602.02839v3 Announce Type: replace Abstract: Enabling robots to perform novel manipulation tasks from natural language instructions remains a fundamental challenge in robotics, despite signific
arXiv:2605.25581v1 Announce Type: new Abstract: Single-cell perturbation prediction aims to infer how cells respond to unseen interventions and to achieve out-of-distribution (OOD) generalization, pro
arXiv:2506.06454v2 Announce Type: cross Abstract: Real-world time series are often governed by complex nonlinear dynamics. Understanding these underlying dynamics is crucial for precise future predict
arXiv:2605.24111v1 Announce Type: cross Abstract: Visual navigation ability is strongly tied to its underlying representation of the world. Unlike classical 3D maps that require globally-consistent ge
arXiv:2605.24961v1 Announce Type: new Abstract: Medical time series are central to healthcare, enabling continuous monitoring and supporting timely clinical decisions. Despite recent progress, existin
arXiv:2510.05699v4 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these a
arXiv:2502.01397v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have been proposed as a tool for learning sparse matrix preconditioners, which are key components in accelerating
arXiv:2605.25439v1 Announce Type: new Abstract: Missing data frequently arises across diverse domains, including time-series and image domains. In the real world, missing occurrences often depend on t
Nano Banana Pro vs. GPT Image 2 Nano Banana Pro wins on photorealism, 4K output, 14 reference image slots for product/scene consistency, and live web search for real-world accuracy. GPT Image 2 wins o
The way we work has fundamentally changed. From automated agents to sophisticated AI services, Generative AI (GenAI) has become a daily tool for a vast majority of employees. But with this rapid adopt
arXiv:2509.15543v2 Announce Type: replace Abstract: Existing decentralized stochastic optimization methods assume the lower-level loss function is strongly convex and the stochastic gradient noise has
arXiv:2311.11342v5 Announce Type: replace Abstract: Stochastic bilevel optimization finds widespread applications in machine learning, including meta-learning, hyperparameter optimization, and neural
arXiv:2605.25554v1 Announce Type: new Abstract: As a core task in intelligent transportation systems, traffic forecasting plays a critical role in urban traffic management. Accurate traffic forecastin
arXiv:2605.25271v1 Announce Type: cross Abstract: We study the symmetric polynomial prod_{alphain A_{n,d}}igl(1+alpha_1 x_1+dots+alpha_n x_nigr) where A_{n,d}:={alphainZ_{ge 0}^n:|alpha|=d}, which is
arXiv:2605.26110v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) achieve versatility by reformulating diverse tasks into a unified instruction-following framework via instruc
arXiv:2605.24295v1 Announce Type: new Abstract: We propose PACE-GGM, a data-adaptive differentially private method for covariance estimation that concentrates its privacy budget on the most informativ
arXiv:2605.23956v1 Announce Type: new Abstract: Compound AI systems that chain multiple LLM calls into directed computation graphs are now the dominant architecture for production AI. Although these a
arXiv:2603.11001v2 Announce Type: replace-cross Abstract: Human uplift studies, or studies that measure the effects of AI access on human performance via randomized controlled trials (RCT) or similar
arXiv:2605.24003v1 Announce Type: cross Abstract: Remote sensing techniques have been increasingly utilised in aquatic applications in recent years. A common challenge in using optical satellite data
arXiv:2605.24394v1 Announce Type: new Abstract: Robotic manipulation of deformable linear objects (DLOs) presents significant challenges due to complex dynamics and frequent self-occlusions. Existing
arXiv:2605.23983v1 Announce Type: new Abstract: We investigate growth dynamics in deterministic equational discovery substrates. Across three toy domains (arithmetic, boolean, higher-order list; n=592
Scan documents with your iPhone 📱, digitalize it with LlamaParse ✍️ We now support parsing HEIC formats natively in LlamaParse (along with 50+ other formats, incl. PDF, Word, Powerpoint, HTML) Try it
arXiv:2605.25424v1 Announce Type: cross Abstract: Existing LLM routing frameworks treat queries as independent events, neglecting the sequential nature of real-world user sessions constrained by globa
arXiv:2605.25680v1 Announce Type: cross Abstract: Language models are increasingly being deployed as user simulators, but their memory is far more reliable than that of real users. To measure this gap
Sakana AI Labs is recruiting software engineers for enterprise-focused roles, with details available on their careers page. The position likely involves developing and maintaining software infrastruct
arXiv:2605.24484v1 Announce Type: new Abstract: Generalist neural routing solvers have shown great potential in solving diverse vehicle routing problems (VRPs) with a unified model. However, existing
arXiv:2605.25648v1 Announce Type: cross Abstract: This paper proposes StrTransformer, a source-wise structured Transformer framework for blind source recovery and branch-wise latent modeling. Instead
arXiv:2605.24452v1 Announce Type: cross Abstract: Legal NLP benchmarks evaluate models on randomly split data, implicitly assuming that legal language is stationary. We test this assumption by fine-tu
The closes thing is METR's very tentative update in February 2026, but the data is not high quality enough to know much of anything. https://metr.org/blog/2026-02-24-uplift-update/#other-means-of-meas
arXiv:2411.00934v2 Announce Type: replace-cross Abstract: Visual content on social media has become increasingly influential in shaping political discourse and civic engagement, but it also limits par
This is our mission. The timeline for achieving this shrinks significantly if we can 10-100x the useful output of our engineering and manufacturing teams. AI and robotics make this possible. This can
arXiv:2605.24873v1 Announce Type: cross Abstract: Despite the importance of causal reasoning, training LLMs to reason causally remains underexplored. Existing data efforts mostly focus on benchmarking
arXiv:2507.21556v3 Announce Type: replace Abstract: The cognitive reality of irregular morphological patterns has been debated for decades: do speakers extend them to novel forms, or are they lexical
arXiv:2605.24842v1 Announce Type: new Abstract: This paper examines how the labour of translators has been transformed into foundational data capital for the age of artificial intelligence (AI). Trans
arXiv:2011.10254v3 Announce Type: replace-cross Abstract: Incomplete multi-view clustering is an important technique to deal with real-world incomplete multi-view data. Previous works assume that all
arXiv:2605.24530v1 Announce Type: new Abstract: Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities. Traditional text-based approache
arXiv:2605.24398v1 Announce Type: cross Abstract: Recent vision-language model (VLM)-based approaches have achieved impressive results on image vectorization tasks. However, they are typically evaluat
arXiv:2509.10452v2 Announce Type: replace Abstract: Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In man
The Windows 95 classic 3D Space Cadet pinball game is being converted from its original digital format into a functional physical pinball machine. The recreation uses largely 3D-printed components inc
arXiv:2512.24000v3 Announce Type: replace Abstract: Distinguishing fake or untrue news from satire or humor poses a unique challenge due to their overlapping linguistic features and divergent intent.
New York Times: A surge in AI-generated “pro se” cases, or lawsuits filed by self-represented litigants, is democratizing the US legal system but consuming more court resources — For years, courts hav
arXiv:2605.23454v1 Announce Type: new Abstract: Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable an
arXiv:2605.23416v1 Announce Type: new Abstract: Acoustic vowel dynamics have some speaker-identifying characteristics, which have been ascribed to individual properties of articulatory strategies: for
arXiv:2605.23473v1 Announce Type: cross Abstract: Bayesian optimization is widely employed for optimizing complex black-box functions but struggles with the curse of dimensionality. Random embedding,
arXiv:2605.23744v1 Announce Type: new Abstract: Anomaly detection in multivariate time series (MTS) is hindered by dynamic inter-variable dependencies and feature entanglement under spectral noise, an
arXiv:2605.23268v1 Announce Type: cross Abstract: In many prediction problems, we have extra information during training (for example, measurements that are expensive or slow to collect) that will not
arXiv:2605.23569v1 Announce Type: new Abstract: Dynamic Programming (DP) and Constraint Programming (CP) are well-established paradigms for solving combinatorial optimization problems. Usually, these
Rack-scale infrastructure has become the defining unit of deployment as enterprises shift from individual servers to fully integrated racks to meet the extreme power and cooling demands of production
arXiv:2605.23328v1 Announce Type: new Abstract: Emotion Recognition in Conversation is a core component of affective computing, while current resources of sign language emotion datasets primarily focu
Written by: Takahiro Sugiyama, Peter Revelant, Mathew Potaczek Introduction In late 2025, Mandiant responded to a security incident involving a compromised web server running KnowledgeDeliver. Knowled
arXiv:2605.22882v1 Announce Type: new Abstract: Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time. As
Grok Build is still in beta for another month or so, but is already quite useful for production tasks Try it out! Favorite features: - <1 second web/X search - Editing and creating assets with Imagine
Grok foundation model V9-Medium (1.5T) has finished training. Evals look good. A lot of Cursor data was added in supplementary training and there is more to come. Fine-tuning is underway and reinforce
arXiv:2605.23422v1 Announce Type: new Abstract: Learning high-quality oblique decision trees remains a significant challenge due to the discrete and non-convex nature of split optimization. We present
arXiv:2605.23651v1 Announce Type: new Abstract: While factual correctness and task-performance have been in focus of Large Language Model (LLM) research for a long time, the fundamental question of ho
arXiv:2508.13663v5 Announce Type: replace Abstract: Methods for query answering over incomplete knowledge graphs retrieve entities that are likely to be answers, which is particularly useful when such
arXiv:2605.23721v1 Announce Type: new Abstract: Classifier-based Quality Filtering has recently emerged as a fundamental technique in constructing pre-training corpora. The ability to deploy a single