Knowledge catalogue
arXiv:2604.11993v1 Announce Type: new Abstract: Illumination using correlated photon sources has been established as an approach to allowing high-fidelity images to be reconstructed from noisy camera
arXiv:2602.02370v2 Announce Type: replace Abstract: Accurate histopathologic interpretation is key for clinical decision-making; however, current deep learning models for digital pathology are often o
arXiv:2604.12149v1 Announce Type: new Abstract: Trajectory optimization depends heavily on initialization. In particular, sampling-based approaches are highly sensitive to initial solutions, and limit
arXiv:2604.11833v1 Announce Type: new Abstract: Despite the popularity of Convolutional Neural Networks (CNN), the problem of uncertainty quantification (UQ) of CNN has been largely overlooked. Lack o
arXiv:2404.14642v4 Announce Type: replace Abstract: Graphical models have demonstrated their exceptional capabilities across numerous applications. However, their performance, confidence, and trustwor
arXiv:2505.14129v2 Announce Type: replace Abstract: Evolution and learning have historically been interrelated topics, and their interplay is attracting increased interest lately. The emerging new fac
arXiv:2604.12817v1 Announce Type: new Abstract: Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To im
arXiv:2601.09313v2 Announce Type: replace-cross Abstract: Language models perform well on grammatical agreement, but it is unclear whether this reflects rule-based generalization or memorization. We s
arXiv:2604.11843v1 Announce Type: new Abstract: Invisible watermarking for autoregressive (AR) image generation has recently gained attention as a means of protecting image ownership and tracing AI-ge
arXiv:2604.12744v1 Announce Type: new Abstract: While multilingual language models promise to bring the benefits of LLMs to speakers of many languages, gold-standard evaluation benchmarks in most lang
arXiv:2604.12346v1 Announce Type: new Abstract: Spatio-temporal video grounding (STVG) aims to localize queried objects within dynamic video segments. Prevailing fully-trained approaches are notorious
arXiv:2604.12208v1 Announce Type: cross Abstract: Global navigation information and local scene understanding are two crucial components of autonomous driving systems. However, our experimental result
arXiv:2603.03249v2 Announce Type: replace Abstract: Generative artificial intelligence (AI) offers scalable support for formative feedback, yet most AI-generated feedback relies on task-specific rubri
arXiv:2604.11913v1 Announce Type: new Abstract: Nutrition estimation of meals from visual data is an important problem for dietary monitoring and computational health, but existing approaches largely
arXiv:2509.17995v2 Announce Type: replace-cross Abstract: Recent advances have shown that scaling test-time computation enables large language models (LLMs) to solve increasingly complex problems acro
arXiv:2505.17384v2 Announce Type: replace-cross Abstract: Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a
arXiv:2512.06443v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed
arXiv:2604.12431v1 Announce Type: cross Abstract: Organisations increasingly outsource privacy-sensitive data transformations to cloud providers, yet no practical mechanism lets the data owner verify
arXiv:2604.12798v1 Announce Type: cross Abstract: FlashAttention-style online softmax enables exact attention computation with linear memory by streaming score tiles through on-chip memory and maintai
arXiv:2604.12887v1 Announce Type: new Abstract: Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what
arXiv:2604.12159v1 Announce Type: new Abstract: The task of video geolocalization aims to determine the precise GPS coordinates of a video's origin and map its trajectory; with applications in forensi
arXiv:2604.12148v1 Announce Type: new Abstract: Video Large Language Models (VideoLLMs) excel at video understanding tasks where outputs are textual, such as Video Question Answering and Video Caption
arXiv:2602.22394v2 Announce Type: replace Abstract: Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, art
arXiv:2604.12044v1 Announce Type: cross Abstract: Deep learning models may converge to suboptimal solutions despite strong validation accuracy, masking an optimization failure we term Trajectory Devia
arXiv:2510.21697v2 Announce Type: replace Abstract: In this paper we show that visual diffusion models can serve as effective geometric solvers: they can directly reason about geometric problems by wo
arXiv:2604.13029v1 Announce Type: cross Abstract: The effectiveness of Direct Preference Optimization (DPO) depends on preference data that reflect the quality differences that matter in multimodal ta
arXiv:2512.22799v2 Announce Type: replace Abstract: Vision-Language Tracking aims to continuously localize objects described by a visual template and a language description. Existing methods, however,
arXiv:2604.12831v1 Announce Type: new Abstract: Indoor fire disasters pose severe challenges to autonomous search and rescue due to dense smoke, high temperatures, and dynamically evolving indoor envi
arXiv:2603.05295v3 Announce Type: replace Abstract: We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible r
arXiv:2603.05044v2 Announce Type: replace Abstract: Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly
arXiv:2604.12540v1 Announce Type: cross Abstract: Data scarcity limits NLP development for low-resource African languages. We evaluate two data augmentation methods -- LLM-based generation (Gemini 2.5
arXiv:2604.11840v1 Announce Type: new Abstract: Large language models are increasingly used as agents in social, economic, and policy simulations. A common assumption is that stronger reasoning should
arXiv:2604.12128v1 Announce Type: new Abstract: We investigate how self-referential inputs alter the internal matrix dynamics of large language models. Measuring 106 scalar metrics across up to 7 anal
arXiv:2604.12007v1 Announce Type: new Abstract: Agent memory systems accumulate experience but currently lack a principled operational metric for memory quality governance -- deciding which memories t
arXiv:2604.12509v1 Announce Type: cross Abstract: Mobile Manipulation (MoMa) of articulated objects, such as opening doors, drawers, and cupboards, demands simultaneous, whole-body coordination betwee
arXiv:2604.12358v1 Announce Type: new Abstract: Recently, visual token pruning has been studied to handle the vast number of visual tokens in Multimodal Large Language Models. However, we observe that
arXiv:2510.20635v2 Announce Type: replace-cross Abstract: Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent advancements of large language models (LLMs
arXiv:2604.05818v2 Announce Type: replace-cross Abstract: Multi-modal Retrieval-Augmented Generation (RAG) has emerged as a highly effective paradigm for Knowledge-Based Visual Question Answering (KB-
arXiv:2604.12025v1 Announce Type: new Abstract: The Semantic Web standardizes concept meaning for humans and machines, enabling machine-operable content and consistent interpretation that improves adv
arXiv:2604.12456v1 Announce Type: cross Abstract: Zero-shot voice conversion (VC) aims to convert a source utterance into the voice of an unseen target speaker while preserving its linguistic content.
arXiv:2604.12140v1 Announce Type: new Abstract: We present XANE(3), a physics-based E(3)-equivariant graph neural network for predicting X-ray absorption near-edge structure (XANES) spectra directly f
arXiv:2604.13001v1 Announce Type: new Abstract: The acquisition of high-quality, action-aligned demonstration data remains a fundamental bottleneck in scaling foundation models for dexterous robot man
arXiv:2507.09318v2 Announce Type: replace-cross Abstract: Generating spoken dialogue is inherently more complex than monologue text-to-speech (TTS), as it demands both realistic turn-taking and the ma
arXiv:2604.11302v1 Announce Type: cross Abstract: We present 3D-Anchored Lookahead Planning (3D-ALP), a System 2 reasoning engine for robotic manipulation that combines Monte Carlo Tree Search (MCTS)
arXiv:2604.09639v1 Announce Type: new Abstract: Artistic style transfer is well studied for images and videos, but extending it to multi-view 3D scenes remains difficult because stylization can disrup
arXiv:2604.11211v1 Announce Type: new Abstract: Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications. We address this
arXiv:2604.10456v1 Announce Type: new Abstract: The surging demand for adapting long-form cinematic content into short videos has motivated the need for versatile automatic video compilation systems.
arXiv:2604.10853v1 Announce Type: new Abstract: Task-oriented evaluation of knowledge graph (KG) quality increasingly asks whether an ontology-based representation can answer the competency questions
arXiv:2604.11540v1 Announce Type: new Abstract: Current large language models require hundreds of billions of parameters yet struggle with domain-specific reasoning and tool coordination in materials
arXiv:2604.11332v1 Announce Type: cross Abstract: Deep learning has markedly advanced image based plant disease diagnosis as improved hardware and dataset quality have enabled increasingly accurate ne
arXiv:2604.09996v1 Announce Type: new Abstract: Accurate apple detection in orchard images is important for yield prediction, fruit counting, robotic harvesting, and crop monitoring. However, changing
arXiv:2604.09676v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for enhancing reasoning in large language models (LLMs), yet scalable training is often hindered
arXiv:2604.10246v1 Announce Type: new Abstract: Photogrammetric 3D reconstruction has long relied on traditional Structure-from-Motion (SfM) and Multi-View Stereo (MVS) methods, which provide high acc
arXiv:2410.11964v2 Announce Type: replace Abstract: The log-linear model has received a significant amount of theoretical attention in previous decades and remains the fundamental tool used for learni
arXiv:2604.10241v1 Announce Type: new Abstract: Identifying the trajectories of rigid bodies and of interaction forces is essential for a wide range of tasks in robotics, biomechanics, and related dom
arXiv:2301.06081v4 Announce Type: replace-cross Abstract: In a variational denoising model, weight in the data fidelity term plays the role of enhancing the noise-removal capability. It is profoundly
arXiv:2604.11279v1 Announce Type: new Abstract: Hyperspectral unmixing (HU) is crucial for analyzing hyperspectral imagery, yet achieving accurate unmixing remains challenging. While traditional metho
arXiv:2604.10650v1 Announce Type: cross Abstract: While the manifold hypothesis is widely adopted in modern machine learning, complex data is often better modeled as stratified spaces -- unions of man
arXiv:2604.10328v1 Announce Type: cross Abstract: Accurate weather nowcasting remains one of the central challenges in atmospheric science, with critical implications for climate resilience, energy se
arXiv:2604.10116v1 Announce Type: cross Abstract: Major depressive disorder (MDD) is a prevalent mental disorder associated with complex neurobiological changes that cannot be fully captured using a s