Knowledge catalogue
arXiv:2605.01967v1 Announce Type: cross Abstract: Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a cha
arXiv:2508.11205v2 Announce Type: replace Abstract: Structure-preserving approaches to dynamics discovery have demonstrated great potential for modeling physical systems due to their use of strong ind
arXiv:2605.01137v1 Announce Type: new Abstract: Metric differential privacy (mDP) strengthens local differential privacy (LDP) by scaling noise to semantic distance, but many machine learning (ML) sys
arXiv:2605.01167v1 Announce Type: new Abstract: Activation steering is a method for controlling Large Language Model (LLM) behavior by intervening in its internal representations to increase the align
arXiv:2605.02014v1 Announce Type: cross Abstract: We introduce Mira, a sample-based score for assessing the accuracy of a candidate conditional distribution using only joint samples from the true data
arXiv:2605.01520v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning
arXiv:2605.01676v1 Announce Type: cross Abstract: Missing data imputation remains a fundamental challenge in modern data science, especially when uncertainty quantification is essential. In this work,
arXiv:2605.01766v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have revolutionized the landscape of AI, demonstrating impressive capabilities in tackling complex vision and
arXiv:2605.02438v1 Announce Type: new Abstract: Open-set supervised anomaly detection (OSAD) aims to identify unseen anomalies using limited anomalous supervision. However, existing prototype-based me
arXiv:2605.01743v1 Announce Type: new Abstract: With the burgeoning development of fields such as the Metaverse, Virtual Reality (VR), and Digital Twins, text-to-3D generation has emerged as a researc
arXiv:2605.01356v1 Announce Type: new Abstract: Learning constraint-satisfying policies from offline data without risky online interaction is crucial for safety-critical decision making. Conventional
arXiv:2605.01580v1 Announce Type: new Abstract: Modern deep learning usually treats models as separate artifacts: trained independently, specialized for particular purposes, and replaced when improved
arXiv:2506.05952v4 Announce Type: replace Abstract: Recent advances in transformer-based text-to-motion generation have led to impressive progress in synthesizing high-quality human motion. Neverthele
arXiv:2605.02351v1 Announce Type: new Abstract: Molecular Vibe Coding, a paradigm where chemists interact with LLMs to generate executable programs for molecular tasks, has emerged as a flexible alter
arXiv:2507.14061v2 Announce Type: replace Abstract: What if a robot could rethink its own morphological representation to better meet the demands of diverse tasks? Most robotic systems today treat the
arXiv:2605.01725v1 Announce Type: new Abstract: Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computat
arXiv:2605.01374v1 Announce Type: new Abstract: Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers
arXiv:2605.01369v1 Announce Type: cross Abstract: Deep learning has been widely adopted for WiFi CSI-based human activity recognition (HAR) due to its ability to learn spatio-temporal features in a pr
arXiv:2605.00885v1 Announce Type: new Abstract: Existing single image dehazing methods have demonstrated satisfactory performance on homogeneous thin-haze images; however, they often struggle with non
arXiv:2605.01219v1 Announce Type: cross Abstract: Audio-visual quality assessment (AVQA) is essential for streaming, teleconferencing, and immersive media. In realistic streaming scenarios, distortion
arXiv:2605.01163v1 Announce Type: cross Abstract: Shared embedding spaces are widely used for multimodal search and data curation. In practice, two problems often limit how well this works. First, emb
arXiv:2605.02471v1 Announce Type: new Abstract: Mapping standing dead trees is crucial for acquiring information on the effects of climate change on forests and forest biodiversity. However, leveragin
arXiv:2503.14505v3 Announce Type: replace Abstract: We introduce MusicInfuser, an approach that aligns pre-trained text-to-video diffusion models to generate high-quality dance videos synchronized wit
arXiv:2601.17756v3 Announce Type: replace Abstract: Existing Subject-to-Video Generation (S2V) methods have achieved high-fidelity and subject-consistent video generation, yet remain constrained to si
arXiv:2605.01075v1 Announce Type: new Abstract: Propagation-based X-ray phase-contrast imaging (PBI) enables high-contrast visualization of lung structures and holds strong medical potential. However,
arXiv:2605.02021v1 Announce Type: new Abstract: Autonomous spacecraft docking requires control policies that simultaneously ensure collision avoidance and target reachability under coupled, high-dimen
arXiv:2605.01745v1 Announce Type: cross Abstract: Language data are increasingly acquired and governed as assets, yet platforms often price candidate resources before knowing their true privacy or acc
arXiv:2510.07731v3 Announce Type: replace-cross Abstract: Organic reaction mechanisms are the stepwise elementary reactions by which reactants form intermediates and products, and are fundamental to u
arXiv:2605.01749v1 Announce Type: new Abstract: Large Reasoning Models achieve strong performance on complex tasks but remain prone to hallucinations, particularly in long-form generation where errors
arXiv:2601.03267v2 Announce Type: replace Abstract: This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers
arXiv:2605.02714v1 Announce Type: new Abstract: The advent of foundation models has heralded a new era in medical artificial intelligence (AI), enabling the extraction of generalizable representations
arXiv:2605.01996v1 Announce Type: new Abstract: Multi-agent motion planning (MAMP) is an important problem for autonomous systems with multiple agents. In this work we propose a two-step method for fi
arXiv:2605.01860v1 Announce Type: new Abstract: This paper explores the benefits of computing arborescent trajectories (trajectory-trees) instead of commonly used sequential trajectories for partially
arXiv:2605.02537v1 Announce Type: new Abstract: Autonomous 3D indoor scene synthesis breaks down in non-convex rooms with tightly coupled spatial constraints. Data-driven generators lack topological p
arXiv:2605.01320v1 Announce Type: new Abstract: LiDAR point cloud compression is vital for autonomous systems to handle massive data from high-resolution sensors. While learned entropy modeling built
arXiv:2605.02069v1 Announce Type: new Abstract: Many scoring applications require absolute predictions, while pairwise comparisons can provide a simpler learning objective. We present Pair2Score, a tw
arXiv:2605.02716v1 Announce Type: new Abstract: Autonomous driving technology has rapidly evolved over the past decade, offering significant improvements in transportation efficiency, safety, and cost
arXiv:2605.02143v1 Announce Type: new Abstract: Personalized federated learning (pFL) aims to adapt models to client specific data distributions, yet it often fails to reliably preserve personalized i
arXiv:2605.00973v1 Announce Type: new Abstract: Biosignals acquired from different locations on the body often provide temporally ordered views of the same underlying physiological process. However, m
arXiv:2605.01003v1 Announce Type: cross Abstract: Statistical change point (CP) detection methods typically rely on likelihood-based inference and ignore contextual information about plausible CP loca
arXiv:2601.00678v2 Announce Type: replace Abstract: Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an ess
arXiv:2605.01759v1 Announce Type: new Abstract: Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models. Des
arXiv:2605.00942v1 Announce Type: cross Abstract: Developing effective test cases capable of thoroughly exercising large-scale software systems is inherently difficult, especially if such systems have
arXiv:2602.11543v2 Announce Type: replace Abstract: Pretraining large language models (LLMs) typically requires centralized clusters with thousands of high-memory GPUs (e.g., H100/A100). Recent decent
arXiv:2605.01625v1 Announce Type: new Abstract: Proteins are inherently multiscale physical systems whose functional properties emerge from coordinated structural organization across multiple spatial
arXiv:2605.01746v1 Announce Type: new Abstract: Single-image 3D face reconstruction is a core problem in computer vision, with important clinical applications such as cephalometric landmark analysis i
arXiv:2605.02144v1 Announce Type: new Abstract: Self-attention in Transformers is typically implemented as softmax(QK^op/sqrt{d})V, where Q=XW_Q, K=XW_K, and V=XW_V are learned linear projections of t
arXiv:2605.01513v1 Announce Type: new Abstract: Designing therapeutic messenger RNA (mRNA) requires creating full-length transcripts that carefully balance stability, translation efficiency, and immun
arXiv:2605.01971v1 Announce Type: new Abstract: Self-supervised learning methods learn high-quality visual representations, yet recent studies show that these representations often capture demographic
arXiv:2405.10271v4 Announce Type: replace Abstract: The practical deployment of Federated Learning (FL) on resource-constrained devices is fundamentally limited by the high cost of training large mode
arXiv:2605.01017v1 Announce Type: new Abstract: We introduce Xiaohongshu Social Comparison Reader Elicitation (XHS-SCoRE), a reader-grounded benchmark for detecting if a text-only Xiaohongshu (RedNote
arXiv:2602.04787v2 Announce Type: replace-cross Abstract: We introduce PuppetAI, a modular soft robot interaction platform. This platform offers a scalable cable-driven actuation system and a customiz
arXiv:2602.02958v4 Announce Type: replace Abstract: Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capabilit
arXiv:2605.01424v1 Announce Type: new Abstract: Multimodal learning leverages the integration of diverse data modalities to enhance performance in complex tasks. Yet, it frequently encounters incomple
arXiv:2605.00901v1 Announce Type: new Abstract: The use of CT imaging is important for screening, diagnosis, therapy planning, and prognosis of lung cancers. Unfortunately, due to differences in imagi
arXiv:2605.02693v1 Announce Type: cross Abstract: Across many scientific disciplines, multiple observations are collected from the same experimental units, and in modern datasets these observations of
arXiv:2510.23199v3 Announce Type: replace-cross Abstract: We consider the best arm identification problem, where the goal is to identify the arm with the highest mean reward from a set of K arms under
arXiv:2605.01393v1 Announce Type: new Abstract: Motion forecasting often requires trading interpretability for predictive accuracy. Standard anchor-based architectures rely on opaque latent queries th
arXiv:2509.10746v3 Announce Type: replace Abstract: Large language models in healthcare often produce emotionally flat or opaque responses, failing to provide the transparent reasoning required for cl
arXiv:2605.01913v1 Announce Type: cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable t