Knowledge catalogue
arXiv:2608.18733v1 Announce Type: cross Abstract: We present Flama, an open-source Python framework for developing and deploying production-ready web APIs, machine learning services, and large-languag
We are thrilled to announce that Google has been recognized as a Leader for the third year in a row in the 2026 Gartner® Magic Quadrant™ for Cloud-Native Application Platforms (CNAP). We believe this
arXiv:2608.19013v1 Announce Type: cross Abstract: Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can a
arXiv:2608.18681v1 Announce Type: new Abstract: We introduce a failure-aware adversarial retrieval-augmented framework for improving robustness in natural language understanding. Rather than selecting
arXiv:2608.18085v1 Announce Type: new Abstract: Prior work has shown that large language models (LLMs) can express diverse personality traits in open-ended text generation. However, it remains unclear
arXiv:2608.19121v1 Announce Type: cross Abstract: Improving molecular properties, such as drug-likeness or binding affinity, is a recurring task in early-stage drug discovery. However, molecules optim
arXiv:2608.19025v1 Announce Type: new Abstract: Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of front
arXiv:2608.18779v1 Announce Type: cross Abstract: Semantic-ID mappings are reusable interfaces between item tokenizers and generative recommenders, yet released mappings rarely state whether they are
arXiv:2603.04448v2 Announce Type: replace Abstract: Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumul
arXiv:2608.19080v1 Announce Type: new Abstract: Object detectors often produce over-confident predictions for objects outside their training categories, leading to so-called out-of-distribution (OoD)
arXiv:2608.19003v1 Announce Type: new Abstract: We ask whether internal representation statistics can provide useful example-level difficulty signals for adaptive inference in multilingual African NLP
arXiv:2608.18931v1 Announce Type: cross Abstract: Test-time scaling (TTS) improves language model outputs by spending additional inference compute - generating multiple candidates, searching over part
arXiv:2608.18836v1 Announce Type: new Abstract: Utilities lose a substantial share of treated water to leakage, yet rarely trust artificial-intelligence localizers to dispatch crews: guessing everywhe
arXiv:2608.18397v1 Announce Type: new Abstract: Wearable stress classifiers can achieve strong average performance while failing completely for a particular individual. On WESAD, a Random Forest reach
arXiv:2512.22287v4 Announce Type: replace-cross Abstract: Synthetic appliance data are essential for developing non-intrusive load monitoring algorithms and enabling privacy preserving energy research
arXiv:2608.17536v1 Announce Type: cross Abstract: Legal consultation questions exhibit multi-level complexity. A single retrieval strategy often leads to over-reasoning for simple questions and poor i
arXiv:2608.17234v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used to interact with screenshots, scanned documents, diagrams, and other visually grounded
arXiv:2602.23088v2 Announce Type: replace Abstract: Vision foundation models increasingly support interactive scientific workflows, but natural-language interaction requires coupling visual representa
arXiv:2608.18034v1 Announce Type: new Abstract: Academic surveys play a central role in organizing rapidly expanding scholarly literature, yet their construction requires extensive paper analysis, coh
arXiv:2608.18058v1 Announce Type: new Abstract: Autonomous LLM agents that converse on a user's behalf are an emerging design pattern in matching platforms, yet their viability depends on a condition
arXiv:2608.17950v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate remarkable multi-hop reasoning capabilities over long contexts, yet the internal mechanisms enabling these dist
arXiv:2505.22104v2 Announce Type: replace Abstract: Shielding has emerged as a promising approach for ensuring safety of AI-controlled autonomous systems. The algorithmic goal is to compute a shield,
arXiv:2608.17646v1 Announce Type: new Abstract: This monograph develops elimination geometry (EG), a typed, native-loss, audit-oriented framework for studying when locally optimal objects can be reali
arXiv:2608.17247v1 Announce Type: new Abstract: Personalized agents must decide whether retrieved user memory should be used, ignored, updated, or queried before it affects a current task. We use this
arXiv:2608.17691v1 Announce Type: new Abstract: Key-keyway assembly tasks impose strict geometric constraints and are highly sensitive to grasp pose deviations in uncertain environments. This work pre
I’ve been looking at a fairly basic question in weight-space learning that I don’t think gets separated cleanly enough: Why does reading semantics directly from neural network weights work pretty well
I have been searching for suitable model to run on my 8GB RAM toy, NVIDIA Orin Nano Super 8GB. This little toy was priced at 249 earlier this year (not any more), and pulls very little power when idle
arXiv:2608.17147v1 Announce Type: cross Abstract: Image-to-image face generators are widely used, and visual dissimilarity between their outputs and source images is sometimes treated as evidence of p
arXiv:2608.17351v1 Announce Type: new Abstract: Open-world face anti-spoofing must address both covariate and semantic shifts: source and target domains differ in imaging conditions, while target doma
arXiv:2608.17981v1 Announce Type: new Abstract: We describe an inference-time architectural enhancement for off-the-shelf foundation models that markedly reduces perplexity and boosts accuracy across
arXiv:2608.17556v1 Announce Type: cross Abstract: Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Exis
arXiv:2604.01460v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, seemingly plausible outputs often suffer
arXiv:2608.16891v1 Announce Type: new Abstract: Agentic AI systems request tool actions that can modify files, send messages, launch jobs, or change workflow state. This shifts the safety problem from
arXiv:2608.17514v1 Announce Type: new Abstract: Vision-language models can describe images fluently, but they often fail to provide actionable photographic critique because semantic content and aesthe
arXiv:2608.17170v1 Announce Type: new Abstract: Algorithm selection for constraint satisfaction problems requires extracting features that capture problem structure. Manually designing feature extract
arXiv:2608.17188v1 Announce Type: cross Abstract: Multi-agent AI workflows are limited not only by model quality but by token cost, latency, and context-window quality. This paper presents a practitio
arXiv:2608.17564v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) are motivated by the hope that understanding and generation reinforce each other but controlled ablations repeatedly
arXiv:2608.14689v1 Announce Type: new Abstract: Residual connections are a fundamental component of transformer architectures, yet the roles of the attention and feed-forward residual pathways remain
arXiv:2608.15456v1 Announce Type: new Abstract: Remote sensing (RS) foundation models provide transferable Earth observation representations across sensors, resolutions, and geographies, yet most rema
arXiv:2608.16873v1 Announce Type: new Abstract: High-fidelity finite-element simulations can provide accurate numerical predictions for side-branch resonators, but large simulation datasets are expens
arXiv:2608.14551v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for title-abstract screening in systematic reviews, but their decisions lack calibrated uncertainty.
arXiv:2608.16336v1 Announce Type: cross Abstract: Modern LLM serving deployments must simultaneously satisfy heterogeneous service-level objectives (SLOs) across a diverse population of user tiers, ra
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:2608.16103v1 Announce Type: new Abstract: Open-vocabulary referring segmentation in 3D Gaussian Splatting (3DGS) requires a neural model to select Gaussian primitives according to free-form lang
arXiv:2501.12434v3 Announce Type: replace-cross Abstract: Motivation: Retrosynthesis plays a crucial role in organic synthesis and drug discovery, focusing on identifying a set of reactants capable of
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:2608.15353v1 Announce Type: new Abstract: Whole-slide image (WSI) report generation requires recognizing spatially distributed pathological features and organizing them into a coherent diagnosti
arXiv:2608.16671v1 Announce Type: new Abstract: The language-model head maps a hidden state of width D to a vocabulary of size V, so its transpose can return at most D independent directions to the Tr
arXiv:2608.16647v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization be
arXiv:2412.09557v3 Announce Type: replace-cross Abstract: Quantum kernel learning (QKL) promises efficient machine learning by encoding feature maps onto exponentially large Hilbert spaces inherent in
arXiv:2507.15502v1 Announce Type: cross Abstract: Postoperative follow-up plays a crucial role in monitoring recovery and identifying complications. However, traditional approaches, typically involvin
arXiv:2608.15812v1 Announce Type: new Abstract: This paper documents a frozen engineering project on personalized Chinese handwriting. The project started from approximately 200 real handwriting image
arXiv:2608.15022v1 Announce Type: new Abstract: Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form when the task requires reusing it fl
arXiv:2608.16733v1 Announce Type: cross Abstract: Physical design algorithms operate within tightly coupled, multi-stage optimization flows, where stage-local gains may vanish or induce downstream deg
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:2608.16712v1 Announce Type: new Abstract: Underactuated tendon-driven hands offer compact actuation and passive compliance, but tendon elongation under restoring-spring loading introduces config
arXiv:2608.15647v1 Announce Type: cross Abstract: Semantic segmentation of very-high-resolution (VHR) remote sensing imagery increasingly benefits from strong pretrained hierarchical encoders, yet exp
arXiv:2608.15400v1 Announce Type: new Abstract: Large Language Models (LLMs) are notorious for struggling with assessing their own uncertainty, detecting knowledge conflicts, or recognizing when probl
arXiv:2608.14870v1 Announce Type: new Abstract: Long-horizon agents can execute continuously, but human attention remains intermittent and scarce. This creates a bidirectional coordination problem: us
arXiv:2608.15964v1 Announce Type: cross Abstract: Language-specific competency (LSC) is the phenomenon of a language model performing better or worse depending on the language of the prompt. In other