Knowledge catalogue
arXiv:2605.30076v1 Announce Type: new Abstract: Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an ef
arXiv:2605.30343v1 Announce Type: cross Abstract: To improve the reasoning capabilities of large language models, test-time compute is typically scaled by generating intermediate tokens before the fin
arXiv:2601.23156v2 Announce Type: replace Abstract: We consider the problem of unsupervised skill segmentation and hierarchical structure discovery in reinforcement learning. While recent approaches h
arXiv:2605.29153v1 Announce Type: cross Abstract: Neural networks trained under different hyperparameter settings can fall into distinct training 'regimes,' with consistent behavior within regimes and
arXiv:2605.30170v1 Announce Type: cross Abstract: While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visu
arXiv:2604.00789v3 Announce Type: replace Abstract: In the previous work, a lexical (re)categorisation -- or confirmation of the given category -- of roots identified as verbal was undertaken to deter
arXiv:2605.30325v1 Announce Type: new Abstract: Scaling Diffusion Transformers to generate high-resolution, long videos is constrained by the quadratic cost of self-attention, and existing sparse atte
arXiv:2605.29302v1 Announce Type: new Abstract: The digital media landscape has seen a pervasive shift toward short-form video advertising on TV, social media and e-commerce platforms. The present stu
arXiv:2605.30167v1 Announce Type: cross Abstract: Predicting a complete spatially correlated field from sparse observations is a fundamental challenge in spatial statistics and environmental modelling
arXiv:2605.29243v1 Announce Type: cross Abstract: Forecasting conversational derailment is the task of predicting, as the conversation unfolds, whether it will eventually derail into personal attacks.
arXiv:2605.30253v1 Announce Type: cross Abstract: We study the contraction in Wasserstein distance of the coordinate ascent variational inference algorithm. This is shown to hold under a transport-inf
arXiv:2512.00837v2 Announce Type: replace Abstract: Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, w
arXiv:2502.20838v3 Announce Type: replace-cross Abstract: Passive acoustic monitoring (PAM) systems generate continuous recordings spanning months, yet automated bioacoustic analysis of whale calls re
arXiv:2605.28823v1 Announce Type: new Abstract: As the influence of LLMs expands, it is imperative to gain insight into their decisions. One way to do that is to develop probes that detect the presenc
arXiv:2605.29828v1 Announce Type: new Abstract: Graph foundation models (GFMs) aim to reuse a single backbone across diverse graph domains, yet their transfer is often uneven and can exhibit negative
arXiv:2605.29025v1 Announce Type: new Abstract: Federal agencies are deploying large language models (LLMs) to categorize public comment corpora, where the model's organization of the record shapes wh
arXiv:2605.29190v1 Announce Type: cross Abstract: Reinforcement learning using verifiable rewards (RLVR) improves LLM reasoning, but the conditions under which it transfers across domains -- and why i
arXiv:2605.30330v1 Announce Type: new Abstract: Diffusion models have excellent capacity to model complex distributions of natural data, which has made them a popular and effective choice for posterio
arXiv:2603.09632v3 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, subsequently extending into numerous spatial AI app
arXiv:2605.29507v1 Announce Type: new Abstract: Explaining why dense retrievers assign high relevance scores remains challenging because retrieval decisions are made through opaque high-dimensional em
arXiv:2605.28575v1 Announce Type: new Abstract: Multimodal Sentiment Analysis (MSA) fuses text, acoustic, and visual streams to infer sentiment. Because pre-trained text encoders are far more expressi
arXiv:2605.28448v1 Announce Type: new Abstract: Optical tweezers (OT) provide piconewton-scale manipulation for delicate biomedical tasks, where visuo-haptic feedback can improve operator awareness by
arXiv:2605.27789v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems are often compared by asking a large language model (LLM) judge which answer is better. For multi-hop RAG,
arXiv:2605.27601v1 Announce Type: cross Abstract: Estimating CPU power on heterogeneous ARM-based commodity devices is challenging due to limited access to CPU's voltage domains. As a result, state-of
arXiv:2605.28619v1 Announce Type: new Abstract: In this work, we present a multiscale kinetic framework for consensus-based image segmentation. By interpreting an image as a system of interacting part
arXiv:2605.28494v1 Announce Type: new Abstract: We describe a new sense-tagged corpus for word sense disambiguation. The corpus is constituted of instances of 20 French polysemous verbs. Each verb ins
arXiv:2605.28151v1 Announce Type: new Abstract: Forest decline driven by climate and biotic stressors threatens ecosystem functioning, making accurate monitoring of tree health essential. In this work
arXiv:2605.28217v1 Announce Type: new Abstract: Pulmonary embolism, the obstruction of a pulmonary artery by a blood clot, is one of the leading causes of acute cardiovascular syndrome. In clinical pr
arXiv:2605.27884v1 Announce Type: new Abstract: City-wide traffic forecasting is important for congestion management, route guidance, and intelligent transportation systems, but accurate prediction re
arXiv:2605.27917v1 Announce Type: new Abstract: Uncrewed Aerial Systems (UASs) have become a growing threat to the security of critical infrastructure, exploiting spatiotemporal gaps in sensor perimet
arXiv:2605.27444v1 Announce Type: cross Abstract: The rapid expansion of space activities has led to an unprecedented accumulation of technical documentation, operational guidelines, and scientific li
arXiv:2603.27459v2 Announce Type: replace Abstract: Arc-standard derivations over projective dependency trees can be interpreted as the incremental construction of lexicalized ordered trees with conti
arXiv:2605.27978v1 Announce Type: new Abstract: We introduce ABot-OCR, an end-to-end vision-language model that transcribes a page image directly into clean Markdown in a single forward pass. By doing
arXiv:2503.09675v3 Announce Type: replace Abstract: Text-based diffusion models have made significant breakthroughs in generating high-quality images and videos from textual descriptions. However, the
arXiv:2505.11638v4 Announce Type: replace-cross Abstract: Natural Gradient Descent (NGD) has emerged as a promising optimization algorithm for training neural network-based solvers for partial differe
arXiv:2605.27556v1 Announce Type: cross Abstract: High-fidelity simulation models are widely used to analyze complex stochastic systems, but their high computational cost motivates the development of
arXiv:2512.22777v2 Announce Type: replace-cross Abstract: Generalization across domains requires stable structure that links the source and target distributions. Building on causal transportability th
arXiv:2605.28127v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) is challenging in long-horizon tasks, where distant state--goal pairs provide weak supervision an
arXiv:2605.28397v1 Announce Type: new Abstract: Predicting conversion from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) is critical for early intervention. Current deep learning paradig
arXiv:2506.12444v2 Announce Type: replace-cross Abstract: In this paper, we propose Adjusted Shuffling SARAH, a novel algorithm that integrates shuffling strategies into the recursive SARAH framework
arXiv:2605.27412v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) have emerged with promising energy-efficient property, yet a substantial performance gap persists compared to Artificia
arXiv:2601.10714v2 Announce Type: replace Abstract: We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, materia
arXiv:2601.10334v2 Announce Type: replace Abstract: Supervised convolutional neural networks (CNNs) are widely used to solve imaging inverse problems, achieving state-of-the-art performance in numerou
arXiv:2605.28001v1 Announce Type: new Abstract: We empirically audit the k-NAF budget-accounting mechanism in Anchored Decoding using (i) a fixed, class-stratified workload (approximately 8,500 random
arXiv:2510.15541v2 Announce Type: replace-cross Abstract: Accurate brain tumor segmentation from MRI is vital for diagnosis and treatment planning. Although Monte Carlo (MC) Dropout is widely used to
arXiv:2605.28428v1 Announce Type: cross Abstract: Detecting subtle visual anomalies in images remains challenging, particularly when only normal samples are available a priori. Such unsupervised anoma
arXiv:2605.28659v1 Announce Type: new Abstract: Biological foundation models have shown strong performance in single-cell representation learning by applying transformer architectures directly to gene
arXiv:2605.27752v1 Announce Type: new Abstract: LLM confidence calibration is often evaluated by comparing two signals: token-probability scores and verbalized confidence. These signals are sometimes
arXiv:2512.01970v3 Announce Type: replace Abstract: Does Reinforcement Learning (RL) merely amplify existing skills, or synthesize novel skills? We investigate this question through the lens of Comple
arXiv:2605.28655v1 Announce Type: new Abstract: Scientific research proceeds through iterative cycles of hypothesis generation, experiment design, execution, and revision. AI agents can automate parts
arXiv:2605.27476v1 Announce Type: cross Abstract: We characterize the pre-softmax attention matrix mathbf{QK^op} in transformers as an associative memory matrix encoding pairwise associations between
arXiv:2605.28131v1 Announce Type: new Abstract: We revisit punctuation-aware tree binarization for constituency parsing and ask whether dependency-induced headedness improves binary parser supervision
arXiv:2605.28004v1 Announce Type: new Abstract: GraphRAG extends retrieval-augmented generation by organizing corpora as explicit knowledge graphs, enabling graph-based retrieval for complex question
arXiv:2605.27715v1 Announce Type: new Abstract: Large reasoning models (LRMs) achieve strong mathematical reasoning performance in English, but remain much less reliable in many low- and medium-resour
arXiv:2605.28022v1 Announce Type: new Abstract: LLMs for code generation are commonly evaluated in repeated-sampling settings using Pass@k, where multiple candidate programs are executed against unit
arXiv:2605.28051v1 Announce Type: new Abstract: Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. Existing methods typically rel
arXiv:2603.10961v2 Announce Type: replace Abstract: Wearable accelerometers enable large-scale health monitoring, yet learning robust human-activity representations has been constrained by scarce labe
arXiv:2605.28739v1 Announce Type: cross Abstract: Tabular data in knowledge-rich domains often carries a latent prior in the form of Boolean implication relationships (BIRs) between pairs of features.
arXiv:2605.27480v1 Announce Type: cross Abstract: Large language model (LLM) serving creates environmental impacts beyond carbon and water, including ecosystem damage through biodiversity-related path
arXiv:2605.28392v1 Announce Type: new Abstract: This study proposes a bound-constrained sparse representation (BC-SR) framework for electrical impedance tomography (EIT), aimed at improving conductivi