Knowledge catalogue
arXiv:2609.15357v1 Announce Type: new Abstract: Diffusion models generate images through an iterative diffusion process, and recent studies have demonstrated that the intermediate feature maps produce
arXiv:2509.24975v4 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) enable parallel generation and are promising for unit test generation (UTG), where efficient and large
arXiv:2609.14596v1 Announce Type: new Abstract: Training-free diffusion inverse solvers typically choose between local measurement guidance and costly clean-space posterior updates. Independent poster
arXiv:2609.13199v1 Announce Type: cross Abstract: Knowledge distillation aims to improve the performance of lightweight student models by transferring knowledge from larger and more powerful teacher m
arXiv:2506.06977v4 Announce Type: replace-cross Abstract: Domain generalization has become a critical challenge in predictive healthcare, where different patient groups exhibit shifting data distribut
arXiv:2609.15973v1 Announce Type: new Abstract: Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning through action, tool use, and outcome fe
arXiv:2609.15903v1 Announce Type: new Abstract: Discrete diffusion and flow models are a promising alternative to autoregressive language models, but compressing many-step sampling into fewer steps ty
arXiv:2609.15975v1 Announce Type: new Abstract: Transformer representations evolve through learned additive transformations that either preserve their current direction or redirect it. We study this e
arXiv:2609.14570v1 Announce Type: cross Abstract: Multi-agent LLM systems combine multiple inference calls, but prior work often confounds how calls are connected with how they are diversified. We stu
arXiv:2606.13105v2 Announce Type: replace Abstract: We revisit the fairness notion of disparate impact for synthetic data generation (SDG), that assesses whether the utility of generated records is th
arXiv:2505.09716v3 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) generalisation is considered a hallmark of human and animal intelligence. To achieve OOD through composition, a syst
arXiv:2609.15266v1 Announce Type: new Abstract: Trajectory curvature constraints are inherent in practical multi-robot systems due to the limited turning capabilities of the robots. Without properly a
arXiv:2609.13909v1 Announce Type: cross Abstract: Continuous-latent Autoregressive Diffusion Transformer (AR-DiT) models have demonstrated immense potential in zero-shot speech generation. However, th
arXiv:2609.13830v1 Announce Type: new Abstract: We present DiVA, a deeply interactive digital life simulator pioneering a new paradigm for long-term, open-ended interactive experiences within digital
arXiv:2609.15609v1 Announce Type: new Abstract: CounterFactual Examples (CFEs) are a cornerstone of eXplainable Artificial Intelligence (XAI), offering local, post hoc, and model-agnostic explanations
arXiv:2609.15383v1 Announce Type: cross Abstract: Language model safety is typically evaluated one interaction at a time. We show that a weaker, unaligned model can split a harmful task into benign-lo
arXiv:2609.15120v1 Announce Type: new Abstract: Benefiting from the powerful generative priors of diffusion models, diffusion-based real-world image super-resolution (Real-ISR) methods have demonstrat
arXiv:2609.13800v1 Announce Type: new Abstract: Routing and cascades reduce tool-agent cost by transferring control across models, but stateful handoffs must preserve accepted choices, realized effect
arXiv:2609.13202v1 Announce Type: new Abstract: Feature engineering has long been a cornerstone of tabular machine learning. Tabular foundation models (TFMs) are pretrained on a wide range of tabular
arXiv:2609.14256v1 Announce Type: new Abstract: Topic models are widely used to analyze public health-related social media short texts, yet their evaluation remains dominated by metrics that focus ent
arXiv:2609.15187v1 Announce Type: new Abstract: Object-Centric Learning (OCL) aims to decompose images into objects without human annotations. A major family of mainstream methods uses Slot Attention
arXiv:2609.13675v1 Announce Type: new Abstract: LiDAR-inertial odometry (LIO) systems differ in whether they continue estimating gravity after initialization. We compare four gravity-bias state config
arXiv:2609.13773v1 Announce Type: cross Abstract: LLM-as-a-Judge evaluators are increasingly used to score open-ended generation, yet a judge's correlation with human ratings on its development set ma
arXiv:2609.14863v1 Announce Type: new Abstract: Smartphone-based Human Activity Recognition (HAR) models often degrade under distribution shifts caused by changes in users, devices, sensor placements,
arXiv:2609.13556v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown remarkable proficiency on general-purpose tasks, yet their performance often degrades in highly-specialized te
arXiv:2609.14571v1 Announce Type: new Abstract: This study highlights the role of domain-specific pretraining profile (DSPP) in Transformer performance for modeling digital pragmatics in Arabic-Englis
arXiv:2511.13368v3 Announce Type: replace-cross Abstract: Large language models (LLMs) perform strongly across tasks and languages, yet how improvements in one task or language affect other tasks and
arXiv:2609.15559v1 Announce Type: cross Abstract: Grammatical error correction (GEC) evaluation has traditionally relied on reference or edit overlap, which can penalize valid rewrites that differ fro
arXiv:2609.13228v1 Announce Type: new Abstract: Vision Language Models (VLMs) should rely on visual evidence that directly determines the correct answer, but supervision for grounding visual reasoning
arXiv:2609.15671v1 Announce Type: cross Abstract: Visual Question Answering (VQA) with Vision-Language Models (VLMs) is increasingly used in privacy-sensitive and bandwidth-constrained settings. Feder
arXiv:2609.15274v1 Announce Type: new Abstract: Kolmogorov-Arnold Networks (KANs) with spline activations have recently shown promise for interpretable function approximation. Distance-Aware Error for
arXiv:2609.14858v1 Announce Type: new Abstract: Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering high-value solutions across com
arXiv:2602.08194v2 Announce Type: replace-cross Abstract: Open-ended learning frames intelligence as emerging from continual interaction with an ever-expanding space of environments. While recent adva
arXiv:2609.14183v1 Announce Type: new Abstract: This paper presents the development and initial testing of DreamSat-Bench, a modular rendezvous and proximity operation testbed designed to benchmark AI
arXiv:2609.13680v1 Announce Type: new Abstract: Fine-tuning instruct models often improves target performance while inducing behavioral drift from the reference model, which can degrade existing capab
arXiv:2609.14312v1 Announce Type: new Abstract: Multi-shell diffusion MRI (dMRI) unlocks more expressive microstructural modeling than single-shell scans, yet its longer acquisition time hinders deplo
arXiv:2609.15861v1 Announce Type: new Abstract: Uncrewed Aerial Manipulators (UAMs) extend the capabilities of Uncrewed Aerial Vehicles (UAVs) from perception to physical interaction. Among various ae
arXiv:2511.20224v3 Announce Type: replace-cross Abstract: Multi-track music generation requires tokens that preserve acoustic fidelity, support sequence modeling, and maintain cross-track structure. R
arXiv:2609.14408v1 Announce Type: new Abstract: We present an automated pipeline that converts NCERT textbooks into interactive video explanations that respond directly to user queries. A user uploads
arXiv:2609.15338v1 Announce Type: cross Abstract: Large Language Models (LLMs) primarily perform inference at the token level, resulting in substantial memory overhead and compromised computational ef
arXiv:2609.15399v1 Announce Type: new Abstract: Although aerial-legged robots offer combined agility and efficiency, controlling high-speed hopping under complex hybrid dynamics is challenging. Reinfo
arXiv:2609.14466v1 Announce Type: new Abstract: Video segmentation models recognize and track objects over time, but they do not indicate whether each segmented region moves independently of the obser
arXiv:2609.14637v1 Announce Type: new Abstract: Large language model agents are increasingly deployed for long-horizon task execution. However, current evaluation paradigms face three major limitation
arXiv:2609.14302v1 Announce Type: new Abstract: Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucination evaluations are mostly clai
arXiv:2609.13191v1 Announce Type: new Abstract: The rapid expansion of operational satellites and orbital debris has increased the frequency of close approach events in low Earth orbit (LEO), creating
arXiv:2609.13533v1 Announce Type: cross Abstract: Most hyperparameter configurations for Evolvable-Substrate HyperNEAT (ES-HyperNEAT) produce networks that stagnate at random-guessing performance, was
arXiv:2507.23600v5 Announce Type: replace Abstract: A single measurement of a chemical mixture, a reaction mixture, a natural extract, or a tissue, records the sum of the profiles of the few component
arXiv:2609.14211v1 Announce Type: cross Abstract: Scientific applications increasingly rely on high-performance computing (HPC), yet translating a scientist's high-level goal into a correct target-sca
arXiv:2512.09944v4 Announce Type: replace Abstract: Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning, y
arXiv:2503.17543v4 Announce Type: replace-cross Abstract: Left ventricular ejection fraction (LVEF) is a primary marker of cardiac function. However, routine estimation from endocardial measurements r
arXiv:2609.14450v1 Announce Type: new Abstract: Cleaning water bodies such as swimming pools and lakes typically demands significant manual effort or reliance on costly, sensor-intensive robotic syste
arXiv:2609.13476v1 Announce Type: cross Abstract: At a 2021 AIM workshop, Guo conjectured that the positive square energy s+ = E+_2 should inherit the familiar edge-addition monotonicity of the spectr
arXiv:2609.14498v1 Announce Type: cross Abstract: Sensor-based human activity recognition (HAR) is fundamental to ubiquitous and wearable computing, yet existing foundation models are largely designed
arXiv:2609.14288v1 Announce Type: new Abstract: Large language models increasingly analyze computational results and draft manuscripts, making reliable communication as important as correct analysis.
arXiv:2609.15171v1 Announce Type: new Abstract: Airborne optical tracking of uncrewed aerial vehicle (UAV) swarms is challenging due to extremely small target scales, rapid viewpoint changes, and clut
arXiv:2609.15687v1 Announce Type: new Abstract: EEG foundation models such as BIOT, LaBraM, and EEGMamba have achieved remarkable performance in neural signal decoding, but their black-box nature limi
arXiv:2609.14839v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into automated code optimization introduces a critical reliability risk we term the Efficiency Halluci
arXiv:2511.03728v2 Announce Type: replace Abstract: On-device AI agents offer the potential for personalized, low-latency assistance, but their deployment is fundamentally constrained by limited memor
arXiv:2609.13440v1 Announce Type: new Abstract: We give a deterministic algorithm for online inverse linear optimization with regret O(d), uniform in the horizon and O(d^{2}) time per round. A bound o
arXiv:2609.13636v1 Announce Type: cross Abstract: Privacy-preserving inference via Torus Fully Homomorphic Encryption (TFHE) provides strong protection for sensitive data in outsourced deep learning a