Knowledge catalogue
arXiv:2512.13998v4 Announce Type: replace-cross Abstract: Music Emotion Recognition (MER) is constrained by limited expert annotations and the need to establish robustness across heterogeneous corpora
arXiv:2607.19857v1 Announce Type: cross Abstract: Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes. In real UAV deployme
arXiv:2607.19714v1 Announce Type: new Abstract: Limbless robots offer exceptional mobility in confined and cluttered environments due to their slender bodies and their ability to exploit body-terrain
arXiv:2607.19686v1 Announce Type: new Abstract: Masked diffusion models (MDMs) are a promising family of language generators, but achieving high-quality few-step generation remains challenging. In MDM
arXiv:2607.17332v2 Announce Type: replace Abstract: Incorporating prior maps significantly enhances the accuracy and robustness of pose estimation in visual-inertial odometry (VIO). However, the large
arXiv:2607.20284v1 Announce Type: new Abstract: The rapid development of multimodal large language models (MLLMs) has introduced a flexible paradigm for remote sensing image scene understanding (RSISU
arXiv:2601.13715v2 Announce Type: replace Abstract: Glass surface ubiquitous in both daily life and professional environments presents a potential threat to vision-based systems, such as robot and dro
arXiv:2607.15702v2 Announce Type: replace-cross Abstract: We develop a non-asymptotic approximation, sampling, and finite-iteration optimization theory for variational physics-informed approximation o
arXiv:2607.20372v1 Announce Type: new Abstract: Humans distill experience into reusable abstractions, e.g., strategies and cautionary reminders, and apply them to gradually solve problems more effecti
arXiv:2607.18504v1 Announce Type: cross Abstract: Benchmarks for Geospatial Foundation Models (GFMs) increasingly rank models by aggregate score, but such rankings obscure why models differ: how much
arXiv:2607.19680v1 Announce Type: cross Abstract: Nuclear quantum effects are rigorously captured by imaginary-time path integrals, which map the quantum Boltzmann distribution onto a ring polymer of
arXiv:2607.18112v2 Announce Type: replace Abstract: Panoptic segmentation in complex scenes remains challenging because of occlusions, yet modern approaches often neglect occlusion modelling. In this
arXiv:2607.20192v1 Announce Type: new Abstract: We study machine unlearning: the removal of memorized training data from a trained model. Specifically, we investigate the algorithmic complexity of cer
arXiv:2509.23937v5 Announce Type: replace-cross Abstract: Diffusion models transform noise into data by injecting information that was captured in their neural network during the training phase. In th
arXiv:2607.19553v1 Announce Type: cross Abstract: We study online optimization for a broad class of structured non-convex non-smooth problems where each loss is a composition of a difference-of-convex
arXiv:2507.03853v2 Announce Type: replace Abstract: We introduce OrbitAll, a geometry- and physics-informed deep learning framework that encodes any molecular system with arbitrary charges, spins, and
arXiv:2607.19895v1 Announce Type: cross Abstract: Text-guided video editing with diffusion models is impractically slow, hindered by costly multi-step sampling and inversion. We present OSVE, the firs
arXiv:2607.19867v1 Announce Type: cross Abstract: FinMMEval 2026 Task 2 evaluates short-answer financial question answering over multilingual evidence. Each final-test item pairs an English question w
arXiv:2509.16727v5 Announce Type: replace Abstract: Automated pain assessment from facial expressions is crucial for non-communicative patient. Progress has been limited by two challenges: (i) existin
arXiv:2607.20389v1 Announce Type: new Abstract: Video captioning requires fine-grained spatio-temporal understanding of videos, including spatial perception of where objects are located and temporal p
arXiv:2607.20230v1 Announce Type: new Abstract: Accurate modeling of environmental systems is fundamental to scientific understanding and decision-making, yet remains challenging because observations
arXiv:2607.17585v2 Announce Type: replace Abstract: Latent diffusion models (LDMs) enable efficient high-resolution image synthesis by denoising in a VAE-compressed latent space. However, fixed visual
arXiv:2603.15403v2 Announce Type: replace Abstract: This paper presents a comprehensive pipeline for recognizing objects targeted by human pointing gestures using RGB images. As human-robot interactio
arXiv:2607.19392v1 Announce Type: new Abstract: Arsenic contamination in groundwater presents a longstanding public health crisis in the United States, especially for households depending on private w
arXiv:2607.20136v1 Announce Type: cross Abstract: Slice-to-volume reconstruction (SVR) is the standard method for obtaining high-resolution (HR) 3D fetal brain volumes from motion-corrupted 2D MRI sli
arXiv:2607.19864v1 Announce Type: cross Abstract: Diabetic retinopathy is a leading cause of preventable blindness; its early lesions are small, low contrast, and easily missed in manual screening. Mo
arXiv:2607.20078v1 Announce Type: new Abstract: We introduce the first dataset that jointly covers both lexical complexity prediction (LCP) annotations and lexical simplification (LS) for Romanian, al
arXiv:2607.19376v1 Announce Type: cross Abstract: Machine learning models trained on biochemical data are routinely evaluated using splits that fail to account for relational structure, causing inform
arXiv:2607.19544v1 Announce Type: cross Abstract: We introduce RELTA-SGLD, a taming scheme that stabilizes superlinear stochastic-gradient updates while reducing unnecessary suppression of the origina
arXiv:2607.19405v1 Announce Type: new Abstract: The CoTFormer architecture formalizes Chain-of-Thought as a form of recurrent latent computation, preserving intermediate states as attendable represent
arXiv:2607.19367v1 Announce Type: new Abstract: Calibration is the primary criterion for evaluating LLM confidence, but it is insufficient: it admits trivially incoherent estimators, depends on the ev
arXiv:2607.19408v1 Announce Type: new Abstract: Using Evolutionary Strategies (ES) for fine-tuning large language models is attractive because it is memory-efficient, parallel, and compatible with bla
arXiv:2607.20033v1 Announce Type: new Abstract: The ability to acquire skills rapidly and effortlessly while retaining those already mastered is essential for robots. However, current methods still re
arXiv:2607.18561v1 Announce Type: cross Abstract: In recent years, multi-view learning has attracted increasing attention, as it integrates the complementary information of heterogeneous views. Most e
arXiv:2607.19776v1 Announce Type: cross Abstract: Existing symbolic music generation models typically use bars as the basic structural unit. However, human perception of musical phrases often does not
arXiv:2509.21028v4 Announce Type: replace Abstract: We introduce SciTrek, a synthetic question-answering dataset for assessing and improving long-context numerical reasoning in large language models (
arXiv:2604.01848v4 Announce Type: replace Abstract: This work investigates the fundamental fragility of state-of-the-art Vision-Language Models (VLMs) under basic geometric transformations. While mode
arXiv:2607.19845v1 Announce Type: cross Abstract: This paper introduces Sentence Splitter, a self-supervised framework built upon a T5-based encoder--decoder architecture for uncovering the latent fac
arXiv:2607.18516v1 Announce Type: cross Abstract: We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure pi^{sign} = (1+alpha)pi^+ - alphapi
arXiv:2607.19943v1 Announce Type: new Abstract: Diffusion Magnetic Resonance Imaging (dMRI) is a powerful tool for probing brain microstructure, but clinical acquisitions are often limited by low out-
arXiv:2607.20402v1 Announce Type: new Abstract: In many reasoning problems, the premises are not observed as discrete symbols, but must be inferred from high-dimensional inputs. Further, the predicate
arXiv:2606.19411v2 Announce Type: replace Abstract: Selecting a small, diverse, high-quality subset from a massive pool of candidates is a recurring primitive in modern machine learning -- data curati
arXiv:2602.13935v2 Announce Type: replace Abstract: While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, parti
arXiv:2607.19459v1 Announce Type: cross Abstract: Modeling galaxy-galaxy strong gravitational lenses to infer the brightness of the source galaxy and the mass distribution of the foreground galaxy is
arXiv:2511.11015v2 Announce Type: replace Abstract: Skip-connected U-Net variants are widely used for dense inverse problems, yet their decoders commonly recover resolution through spatial upscaling,
arXiv:2607.18436v1 Announce Type: new Abstract: Streaming autoregressive diffusion makes minute-scale video synthesis practical, but its bounded context and fixed denoising schedule allocate resources
arXiv:2603.18634v3 Announce Type: replace-cross Abstract: Rapid, large-scale 3D reconstruction from multi-date satellite imagery is vital for environmental monitoring, urban planning, and disaster res
arXiv:2607.19535v2 Announce Type: new Abstract: Incorrect disposal can contaminate campus recycling streams, and a bin-mounted camera could provide feedback as an item is discarded. We evaluated wheth
arXiv:2607.20003v1 Announce Type: cross Abstract: An increase in advanced Android malware requires the use of deep learning models, which can run on Android devices. But there is a trade-off between s
arXiv:2607.14702v2 Announce Type: replace Abstract: Automatic recognition of ambivalence and hesitancy is challenging because these states may be expressed through inconsistent linguistic, acoustic, f
arXiv:2607.19503v1 Announce Type: cross Abstract: A quantum-inspired tensor network framework for wildfire susceptibility classification in the Gargano region is introduced, leveraging AlphaEarth embe
arXiv:2607.20351v1 Announce Type: cross Abstract: We find that vision-language models are sensitive to a specific semantically irrelevant change: the order in which the image and question are presente
arXiv:2607.19139v1 Announce Type: new Abstract: Text-to-image diffusion transformers (DiTs) jointly process text and image tokens, yet their internal computation during denoising remains poorly unders
arXiv:2607.19526v1 Announce Type: new Abstract: 'Stop Chasing the C-index when Evaluating Survival Analysis Models' (ICML 2026, Spotlight) argued normatively, on synthetic data, that evaluating surviv
arXiv:2607.16274v2 Announce Type: replace Abstract: Joint-Embedding Predictive Architectures (JEPAs) train a predictor jointly with their encoder, but downstream deployment discards the predictor and
arXiv:2607.19390v1 Announce Type: new Abstract: A recent report finds that orthogonalizing the mLSTM memory matrix at read time (five Newton-Schulz iterations, trained through) substantially improves
arXiv:2512.03854v2 Announce Type: replace Abstract: Artificial intelligence (AI) is increasingly used in digital pathology. Publicly available histopathology datasets remain scarce, and those that do
arXiv:2607.20201v1 Announce Type: cross Abstract: Additive models buy interpretability by forbidding feature interactions, a constraint that neural instantiations enforce architecturally. We introduce
arXiv:2503.18219v2 Announce Type: replace Abstract: This work studies the sampling complexity of learning with ReLU neural networks and neural operators. For mappings belonging to relevant approximati
arXiv:2511.12035v2 Announce Type: replace-cross Abstract: The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video g