Knowledge catalogue
arXiv:2605.13790v1 Announce Type: cross Abstract: Partial differential equations (PDEs) are fundamental for modeling complex natural and physical phenomena. In many real-world applications, however, o
arXiv:2605.12522v1 Announce Type: cross Abstract: Diffusion language models (DLMs) are promising alternatives to autoregressive language models (ARMs), yet the intrinsic differences in their generated
arXiv:2512.13399v2 Announce Type: replace Abstract: Crafting effective reward signals remains a central challenge in Reinforcement Learning (RL), especially for complex reasoning tasks. Existing autom
arXiv:2605.13282v1 Announce Type: new Abstract: Classical planners can effectively solve very large deterministic MDPs represented in STRIPS or PDDL where states are sets of atoms over objects and rel
arXiv:2511.01303v2 Announce Type: replace-cross Abstract: We consider the problem of constructing differentially private nonparametric confidence intervals (CIs) for an arbitrary quantity using resamp
arXiv:2605.13182v1 Announce Type: new Abstract: Diffusion-based models have shown strong performance in video super-resolution (VSR) and video frame interpolation (VFI). However, their role in the cou
arXiv:2602.08920v2 Announce Type: replace Abstract: Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre
arXiv:2602.06021v2 Announce Type: replace-cross Abstract: We study a data-dependent notion of diffusion-model generalization: when a model does not memorize the training set, where do its generated sa
arXiv:2605.13115v1 Announce Type: cross Abstract: Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor atta
arXiv:2605.12832v1 Announce Type: cross Abstract: Single-arm trials are an important study design for evaluating drug efficacy and safety without enrolling patients into a control arm. Although they d
arXiv:2605.12939v1 Announce Type: new Abstract: Recent diffusion- and flow-based VTON methods achieve strong results with pretrained generative models, but their reliance on multi-step sampling incurs
arXiv:2605.12702v1 Announce Type: new Abstract: General-purpose safety benchmarks for large language models do not adequately evaluate disability-related harms. We introduce DisaBench: a taxonomy of t
arXiv:2605.13708v1 Announce Type: cross Abstract: Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secur
arXiv:2602.03429v2 Announce Type: replace Abstract: To handle ambiguous and open-ended requests, Large Language Models (LLMs) are increasingly trained to interact with users to surface intents they ha
arXiv:2605.13484v1 Announce Type: cross Abstract: Calibration is commonly evaluated by comparing model confidence with its empirical correctness, implicitly treating reliability as a function of the c
arXiv:2605.13296v1 Announce Type: new Abstract: Multi-Agent Path Finding (MAPF) is a coordination problem that requires computing globally consistent, collision-free trajectories from individual start
arXiv:2605.12805v1 Announce Type: cross Abstract: MeanFlow enables one-step generation in continuous spaces by learning an average velocity over a time interval rather than the instantaneous velocity
arXiv:2605.12836v1 Announce Type: new Abstract: Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on
arXiv:2605.13731v1 Announce Type: new Abstract: Generative artificial intelligence (AI) is increasingly being integrated into education, where it can boost learners' performance. However, these uses d
arXiv:2605.12574v1 Announce Type: cross Abstract: Vision-language models (VLMs) are trained on large-scale image-text corpora that may contain private, copyrighted, or otherwise sensitive data, motiva
arXiv:2602.06713v2 Announce Type: replace-cross Abstract: Missing data imputation, where a model is trained on observed data to estimate unobserved values, is a fundamental problem in machine learning
arXiv:2605.12974v1 Announce Type: new Abstract: In this work, we study how to ensure probabilistic safety for nonlinear systems under distributional ambiguity. Our approach builds on a backup-based sa
arXiv:2605.12649v1 Announce Type: new Abstract: Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and highl
arXiv:2605.13332v1 Announce Type: new Abstract: Argumentation is an important topic of AI for modelling and reasoning about arguments. In abstract argumentation, we consider directed graphs, so-called
arXiv:2509.13316v4 Announce Type: replace-cross Abstract: Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verb
arXiv:2605.12673v1 Announce Type: new Abstract: Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hackin
arXiv:2605.12701v1 Announce Type: cross Abstract: Machine learning algorithms in socially sensitive domains (e.g., credit decisions) often focus on equalizing predictive outcomes. However, satisfying
arXiv:2605.13175v1 Announce Type: new Abstract: Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering t
arXiv:2605.12623v1 Announce Type: cross Abstract: Multilingual document understanding remains limited for low-resource languages due to scarce training data and model-based annotation pipelines that p
arXiv:2605.13179v1 Announce Type: new Abstract: The Engram module -- a hash-keyed, O(1) associative memory injected into Transformer layers -- was recently shown to improve large language model pretra
arXiv:2605.13084v1 Announce Type: cross Abstract: Meta-learning has been shown to have better performance than supervised learning for few-shot monolingual spoken word classification. However, the met
arXiv:2605.12516v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) often struggle to generate reliable responses in specialized engineering domains due to limited domain gr
arXiv:2605.13418v1 Announce Type: new Abstract: Differentially private optimization suffers from a fundamental geometric mismatch: deep networks have highly anisotropic loss landscapes, yet DP-SGD inj
arXiv:2605.12994v1 Announce Type: new Abstract: We study differentially private (DP) training with Muon, a matrix-valued optimizer that updates hidden-layer weights using momentum followed by Newton--
arXiv:2605.13349v1 Announce Type: new Abstract: Diffusion-based point editing methods have gained significant traction in image editing tasks due to their ability to manipulate image semantics and fin
arXiv:2605.12998v1 Announce Type: new Abstract: Continual graph learning (CGL) aims to learn from dynamically evolving graphs while mitigating catastrophic forgetting. Existing CGL approaches typicall
arXiv:2605.12625v1 Announce Type: cross Abstract: Continuous-action policies trained on a single demonstrated trajectory per scene suffer from mode collapse: samples cluster around the demonstrated ma
arXiv:2605.13156v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated remarkable capabilities in bridging visual perception and natural language understanding, enabling a wid
arXiv:2605.13568v1 Announce Type: cross Abstract: Myocardial infarction (MI) is a leading cause of death, and its adverse outcomes are urgent to predict. Yet ECG-based prognostic models underperform b
arXiv:2605.13192v1 Announce Type: new Abstract: This paper presents a motion analysis framework for an athlete wearing sport-specific flexible prosthesis based on the soft-rigid hybrid-link system. Su
arXiv:2605.12897v1 Announce Type: new Abstract: DynoJEPP is a factor-graph-based framework that jointly formulates and simultaneously optimizes estimation, prediction, and planning in dynamic environm
arXiv:2605.12705v1 Announce Type: new Abstract: How can we train models whose post-trained capabilities survive subsequent fine-tuning? Rather than focusing on downstream interventions to mitigate for
arXiv:2605.13122v1 Announce Type: new Abstract: Instruction-based image editing (IIE) models have recently demonstrated strong capability in modifying specific image regions according to natural langu
arXiv:2605.12542v1 Announce Type: cross Abstract: Large foundation models (FMs) are transforming Earth science by integrating heterogeneous multimodal data, such as multi-platform imagery, gridded rea
arXiv:2605.13194v1 Announce Type: cross Abstract: Electrocardiogram (ECG) arrhythmia classification remains challenging due to signal variability, noise, limited labeled data, and the difficulty in ac
arXiv:2605.12887v1 Announce Type: cross Abstract: Web-enabled LLM agents are changing how online information influences search outcomes. Existing Generative Engine Optimization (GEO) studies mainly fo
arXiv:2605.13062v1 Announce Type: new Abstract: Recent image editing models have achieved remarkable progress in instruction following, multimodal understanding, and complex visual editing. However, e
arXiv:2509.13858v2 Announce Type: replace Abstract: Dataset distillation aims to synthesize a compact dataset from the original large-scale one, enabling highly efficient learning while preserving com
arXiv:2605.13485v1 Announce Type: new Abstract: Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representation
arXiv:2505.17469v2 Announce Type: replace-cross Abstract: Compression and generalization are fundamentally related through Solomonoff induction and the minimum description length principle (MDL), whic
arXiv:2502.05157v3 Announce Type: replace Abstract: The perspective of developing trustworthy AI for critical applications in science and engineering requires machine learning techniques that are capa
arXiv:2602.03730v2 Announce Type: replace-cross Abstract: Generative foundation models trained on tokenized electronic health record (EHR) timelines show promise for clinical outcome prediction via Mo
arXiv:2605.13462v1 Announce Type: new Abstract: Gesture recognition is a cornerstone of Human-Computer Interaction (HCI) for smart eyewear, enabling natural and device-free control in augmented realit
arXiv:2605.13335v1 Announce Type: new Abstract: Embodied agents in household environments must plan under partial observation: they need to remember objects, track state changes, and recover when acti
arXiv:2605.13041v1 Announce Type: new Abstract: With recent advances in embodied agents and AR devices, egocentric observations are readily available as input for real-world interactive online applica
arXiv:2602.05242v1 Announce Type: cross Abstract: Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bu
arXiv:2605.12920v1 Announce Type: cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's e
arXiv:2605.13315v1 Announce Type: cross Abstract: Biological neural networks (BNNs) have been established as a powerful and adaptive substrate that offer the potential for incredibly energy and data e
arXiv:2605.12798v1 Announce Type: cross Abstract: Fine-tuning LLMs on narrow harmful datasets can induce Emergent Misalignment (EM), where models exhibit misaligned behavior far beyond the fine-tuning
arXiv:2605.13247v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models offer a powerful way to scale model size without increasing compute, as per-token FLOPs depend only on k active e