Knowledge catalogue
arXiv:2605.03780v1 Announce Type: cross Abstract: Transformers are effective at inferring the latent task from context via two inference modes: recognizing a task seen during training, and adapting to
arXiv:2605.03045v1 Announce Type: new Abstract: Causal Discovery (CD) is a powerful framework for scientific inquiry. Yet, its practical adoption is hindered by a reliance on strong, often unverifiabl
arXiv:2605.03237v1 Announce Type: cross Abstract: Project-based learning improves student engagement and learning outcomes, yet allocating students to appropriately challenging projects while forming
arXiv:2605.03712v1 Announce Type: cross Abstract: Training-free conditional diffusion provides a flexible alternative to task-specific conditional model training, but existing samplers often allocate
arXiv:2605.02024v1 Announce Type: new Abstract: In Dung-style abstract argumentation, various semantics capture notions of acceptability of arguments. The admissibility semantics capture the notion th
arXiv:2602.21204v3 Announce Type: replace-cross Abstract: Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a
arXiv:2605.03245v1 Announce Type: cross Abstract: Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature pre
arXiv:2408.12622v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet resea
arXiv:2509.10577v3 Announce Type: replace-cross Abstract: We study a basic question about cryptographic watermarking for generative models: how reliable can a watermark remain when an adversary is all
arXiv:2605.02244v1 Announce Type: cross Abstract: Frontier software engineering agents have saturated short-horizon benchmarks while regressing on the work that constitutes senior engineering: long-ho
arXiv:2605.00914v1 Announce Type: cross Abstract: Multi-agent debate, where teams of LLMs iteratively exchange rationales and vote on answers, is widely deployed under the assumption that peer review
arXiv:2605.03936v1 Announce Type: new Abstract: Conceptual analysis -- proposing definitions and refining them through counterexamples -- is central to philosophical methodology. We study whether lang
arXiv:2605.02681v1 Announce Type: cross Abstract: We present two new classes of causal models of decision-making agents. Our approach is motivated by the needs of modeling the economics of computing s
arXiv:2605.03642v1 Announce Type: new Abstract: Open-vocabulary object detection aims to recognize objects from an open set of categories, which leverages vision-language models (VLMs) pre-trained on
arXiv:2605.02106v1 Announce Type: new Abstract: Contemporary artificial intelligence systems achieve strong performance through large-scale parameterization, retrieval augmentation, and training on ex
arXiv:2508.15524v3 Announce Type: replace Abstract: We present the first large-scale computational study of political delegitimization discourse (PDD), defined as symbolic attacks on the normative val
arXiv:2605.01245v1 Announce Type: cross Abstract: Narrative archetypes (e.g., Hero's Journey, Three-act structure) provide universal story structures that resonate across cultures and media and are im
arXiv:2605.03816v1 Announce Type: cross Abstract: The Brier score conflates two distinct properties of probabilistic predictions: reliability (calibration error) and resolution (discriminatory power).
arXiv:2605.00844v1 Announce Type: cross Abstract: When large language models (LLMs) are consulted as forecasting tools, the independence of individual errors -- the foundation of collective intelligen
arXiv:2505.16932v5 Announce Type: replace-cross Abstract: Computing the polar decomposition and the related matrix sign function has been a well-studied problem in numerical analysis for decades. Rece
arXiv:2605.01160v1 Announce Type: cross Abstract: Since 2022, AI-powered coding assistants have produced contradictory evidence: controlled studies report 20-56% productivity gains on well-scoped task
arXiv:2605.03258v1 Announce Type: cross Abstract: Large language models often fail at simple counting tasks, even when the items to count are explicitly present in the prompt. We investigate whether t
arXiv:2605.03073v1 Announce Type: new Abstract: Niche-domain Indic ASR -- digit strings, currency amounts, addresses, brand names, English/Indic codemix -- is under-served by both open-source SOTA and
arXiv:2605.01418v1 Announce Type: new Abstract: Time-series generative models often lack control over temporal granularity, forcing users to accept whatever granularity the model produces. To enable t
arXiv:2605.01809v1 Announce Type: cross Abstract: Unified audio-visual generation is rapidly gaining industrial and creative relevance, enabling applications in virtual production and interactive medi
arXiv:2605.01134v1 Announce Type: new Abstract: The dominant noun-based modeling paradigm has fundamentally constrained AI development, precluding any adequate representation of the future as an open
arXiv:2605.00922v1 Announce Type: cross Abstract: There has been intense debate among qualitative researchers about whether generative AI is suitable for qualitative research. In this paper, we summar
arXiv:2603.25169v2 Announce Type: replace Abstract: LLM performance is highly sensitive to prompt design, yet whether automatic prompt optimization can replace expert prompt engineering in linguistic
arXiv:2510.09511v2 Announce Type: replace-cross Abstract: Variable stiffness is a key capability in biological and robotic systems, enabling adaptive interaction across tasks and environments. Mechani
arXiv:2604.25000v2 Announce Type: replace Abstract: Recent work has framed intelligence in verifiable tasks as reducing time-to-solution through learned structure and test-time search, while systems w
arXiv:2603.06440v2 Announce Type: replace Abstract: We study a practical question in generative quantum machine learning: given a classical dataset, can we determine, before training, whether it is we
arXiv:2605.03348v1 Announce Type: new Abstract: We propose S3 (Specialization, Selection, Sparsification), a framework that rethinks multimodal learning through a structural perspective. Instead of en
arXiv:2605.03802v1 Announce Type: cross Abstract: ML climate model emulators are useful for scenario planning and adaptation, allowing for cost-efficient experimentation. Recently, the diffusion model
arXiv:2408.01055v2 Announce Type: replace-cross Abstract: Self-healing systems have long been a focus of research, aiming to enable software to recover from unexpected runtime errors without human int
arXiv:2605.02901v1 Announce Type: cross Abstract: This work aims to establish an end-to-end system for tracking of physical 3D objects for virtual reality (VR) applications. We focus on training appli
arXiv:2605.01102v1 Announce Type: new Abstract: Single-agent systems (SAS) have become the default pattern for LLM-driven scientific workflows, but routing planning, tool use, and synthesis through a
arXiv:2603.17368v2 Announce Type: replace Abstract: Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning cap
arXiv:2605.02269v1 Announce Type: new Abstract: Specification gaming is a critical failure mode of LLM agents. Despite this, there has been little systematic research into when it arises and what driv
arXiv:2605.03838v1 Announce Type: new Abstract: We introduce TRACE, a cross-domain engineering framework for trustworthy agentic AI in operationally critical domains. TRACE combines a four-layer refer
arXiv:2605.03358v1 Announce Type: new Abstract: When orthodontists trace cephalometric radiographs, they follow a structured workflow: identify the soft tissue profile, partition the skull into anatom
arXiv:2605.02958v1 Announce Type: cross Abstract: Representation Engineering typically relies on static refusal vectors derived from terminal representations. We move beyond this paradigm, demonstrati
arXiv:2605.03789v1 Announce Type: cross Abstract: We propose Conformal Seasonal Pools (CSP), a training-free probabilistic time-series forecaster that mixes same-season empirical draws with signed res
arXiv:2511.14887v2 Announce Type: replace Abstract: The rapid advancement of electric vertical takeoff and landing (eVTOL) aircraft offers a promising opportunity to alleviate urban traffic congestion
arXiv:2605.03953v1 Announce Type: cross Abstract: Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low
arXiv:2605.03792v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into legal workflows. However, existing benchmarks primarily address proxy tasks, such as bar e
arXiv:2605.01970v2 Announce Type: cross Abstract: Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characte
arXiv:2605.02640v1 Announce Type: new Abstract: As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), is increasingly deployed in high-stakes domains, en
arXiv:2605.01329v1 Announce Type: new Abstract: In-group favoritism refers to the phenomena of favoring members of one's in-group over out-group members and is widely observed in numerous social coope
arXiv:2605.03405v1 Announce Type: new Abstract: Attacking semantic segmentation models is significantly harder than image classification models because an attacker must flip thousands of pixel predict
arXiv:2605.01999v1 Announce Type: new Abstract: Classifying brain tumors using magnetic resonance imaging (MRI) is crucial for early diagnosis and treatment; however, tumor heterogeneity and a dearth
arXiv:2605.03379v1 Announce Type: cross Abstract: Repeated sampling is a standard way to spend test-time compute, but its benefit is controlled by the latent distribution of correctness across example
arXiv:2605.03950v1 Announce Type: new Abstract: Although recent LMMs have become much stronger at visual perception, they remain unreliable on problems that require multi-step reasoning over visual ev
arXiv:2605.01257v1 Announce Type: new Abstract: Large-scale GPS trajectory data offer rich observations of human mobility, yet assigning trip purposes to detected stops remains challenging due to the
arXiv:2605.03614v1 Announce Type: new Abstract: Visual affordances identify regions in an image with potential interactions, offering a novel paradigm for scene understanding. Recognizing affordances
arXiv:2601.14505v2 Announce Type: replace-cross Abstract: In the network security domain, due to practical issues -- including imbalanced data and heterogeneous legitimate network traffic -- adversari
arXiv:2502.04419v3 Announce Type: replace-cross Abstract: Generating synthetic datasets via large language models (LLMs) has emerged as a promising approach to improve LLM performance. However, LLMs i
arXiv:2605.03517v1 Announce Type: new Abstract: Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework th
arXiv:2605.03677v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models
arXiv:2605.04044v1 Announce Type: new Abstract: Visual correspondence across image-to-image (2D-2D), image-to-point cloud (2D-3D), and point cloud-to-point cloud (3D-3D) geometric matching forms the f
arXiv:2605.03716v1 Announce Type: new Abstract: Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing met