Knowledge catalogue
arXiv:2608.20467v1 Announce Type: cross Abstract: Safety filters are an effective tool for enforcing constraints in safety-critical systems, but most existing methods assume perfect state information,
arXiv:2608.20354v1 Announce Type: cross Abstract: This study introduces NeuroStrata, a connectivity-aware deep representation learning framework for EEG-based mental stress analysis using Time-Varying
arXiv:2608.21254v1 Announce Type: new Abstract: Accurate agricultural weed detection in real-world field conditions is essential for precision agriculture, enabling targeted intervention and reducing
arXiv:2608.21349v1 Announce Type: cross Abstract: Scarce data and tumor heterogeneity limit patient-level cancer treatment-response prediction. Existing approaches predict response from pretreatment m
arXiv:2608.20916v1 Announce Type: new Abstract: Vision foundation models (VFMs) offer strong generalization capabilities for domain-adaptive object detection (DAOD). However, existing VFM-based method
arXiv:2608.20421v1 Announce Type: cross Abstract: Large language models (LLMs) are now embedded in scientific, educational, and governance workflows, with debates centering on their capabilities, mech
arXiv:2608.20378v1 Announce Type: new Abstract: Safety alignment in Large Language Models (LLMs) is often superficial, relying on refusal mechanisms that trigger only at the final stages of generation
arXiv:2608.21098v1 Announce Type: new Abstract: Fusing prior knowledge with data-driven learning is attractive where data is scarce, yet no controlled account says when it helps, is redundant, or harm
arXiv:2608.19504v1 Announce Type: new Abstract: We propose a conditioning mechanism for diffusion models based on multi-speed joint diffusion of the target and the condition. The mechanism learns an u
arXiv:2608.19779v1 Announce Type: cross Abstract: World models provide digital simulacra of the true world, allowing agents to be trained and tested before costly real-world deployment. At each time s
arXiv:2606.23487v2 Announce Type: replace Abstract: Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as
arXiv:2512.07847v2 Announce Type: replace Abstract: Benchmarking has been the cornerstone of progress in computer vision, natural language processing, and the broader deep learning domain, driving alg
arXiv:2608.19491v1 Announce Type: cross Abstract: Most modern optimizers form their momentum as an exponential moving average (EMA) of past gradients, forgetting every direction at one fixed rate. How
arXiv:2608.19376v1 Announce Type: cross Abstract: Split-conformal prediction provides marginal coverage under exchangeability and is increasingly used as an abstention layer for zero-shot vision-langu
arXiv:2608.20315v1 Announce Type: new Abstract: Predictive models over structured electronic health records (EHRs) remain central to machine learning for healthcare, but few have jointly emphasized qu
arXiv:2608.19490v1 Announce Type: cross Abstract: State-of-the-art vision-language-action (VLA) models such as pi_{0.5} exhibit strong semantic understanding, instruction following and task behavior.
arXiv:2608.20112v1 Announce Type: cross Abstract: Generative models have shown strong potential for positron emission tomography (PET) image reconstruction. Although diffusion model-based reconstructi
arXiv:2608.20281v1 Announce Type: cross Abstract: Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time
arXiv:2608.20061v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures significantly expand model capacity without a proportional increase in computational cost. However, optimizing
arXiv:2608.20202v1 Announce Type: new Abstract: Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions. However, existing
arXiv:2608.19666v1 Announce Type: new Abstract: Deep learning-based whole-body PET-CT lesion segmentation can support cancer staging, treatment planning, and response assessment, but generalization is
arXiv:2506.07459v4 Announce Type: replace Abstract: Protein generative models have shown remarkable promise in protein design, yet their success rates remain constrained by reliance on curated sequenc
arXiv:2608.20099v1 Announce Type: cross Abstract: LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substant
arXiv:2608.19238v1 Announce Type: cross Abstract: Spiking Transformers model token interactions primarily through spiking self-attention (SSA). However, binary query and key representations map contin
arXiv:2608.19200v1 Announce Type: cross Abstract: Text summarization refers to the task of condensing a document into a shorter version while preserving its key information. Automatic text summarizati
arXiv:2608.20054v1 Announce Type: new Abstract: Multi-module systems often expose every module to the full input. We test whether restricting evidence visibility changes which solutions gradient-based
arXiv:2608.18709v1 Announce Type: cross Abstract: Foundation models are increasingly breaking what seemed to be impossible not long ago by enabling unprecedented accuracy and cross-domain generalizati
arXiv:2608.18731v1 Announce Type: cross Abstract: Medical image segmentation is essential for clinical workflows such as treatment planning and disease assessment. While specialist tools like TotalSeg
arXiv:2608.18132v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are typically built through a multi-stage pipeline consisting of cross-modal alignment, supervised fine-tuning
arXiv:2608.19004v1 Announce Type: cross Abstract: Site-specific weed management in paddy farming offers substantial reductions in herbicide use over conventional broadcast spraying, but field deployme
arXiv:2608.18242v1 Announce Type: new Abstract: We introduce ClosureBench, a constructive benchmark for compositional graph-relational reasoning with programmatically verified ground truth. Unlike fix
arXiv:2608.19133v1 Announce Type: new Abstract: We present a novel application of embedding-based dynamic topic modeling techniques to detect and quantify topic drift at the comment level in a massive
arXiv:2608.18515v1 Announce Type: new Abstract: Transvaginal ultrasound (TVUS) and magnetic resonance imaging (MRI) provide complementary information for endometriosis image analysis, yet existing stu
arXiv:2608.18711v1 Announce Type: new Abstract: Egocentric vision systems capture human behavior from visible cues, but overlook physiological indicators of autonomic states such as stress, engagement
arXiv:2608.19174v1 Announce Type: cross Abstract: This technical report describes our winning submission to the AES AIMLA 2025 Challenge on querying sound effects by vocal imitation. We investigate tw
arXiv:2607.18197v2 Announce Type: replace Abstract: Seamless human-robot interaction (HRI) requires a number of perceptual and motor abilities from the robot, one of them being the imitation of human
arXiv:2608.18274v1 Announce Type: cross Abstract: OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and
arXiv:2608.18401v1 Announce Type: cross Abstract: Evaluating interaction quality in real-world HRI is an important challenge. If interaction quality can be estimated reliably, the results can be used
arXiv:2608.18367v1 Announce Type: cross Abstract: Accurate localization and segmentation of the optic disc (OD) are important for retinal image analysis and glaucoma assessment, yet remain challenging
arXiv:2608.18669v1 Announce Type: new Abstract: Humans solve complex problems by constructing plans and mentally simulating their outcomes with an internal model of the world. Machine learning has pro
arXiv:2608.18282v1 Announce Type: cross Abstract: Stochastic mean-field control (MFC) provides a fundamental framework for coordinating large populations of interacting agents under uncertainty, with
arXiv:2608.19197v1 Announce Type: cross Abstract: Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environ
arXiv:2608.18437v1 Announce Type: new Abstract: Tangut is an extinct language whose script does not explicitly mark word boundaries. We present the first systematic study of Tangut word segmentation u
arXiv:2608.18715v1 Announce Type: cross Abstract: Ensuring not only high accuracy but also reliable and robust predictions is critical for the deployment of semantic segmentation models in safety-crit
arXiv:2608.18825v1 Announce Type: cross Abstract: Medical automatic speech recognition (MedASR) requires adaptation to specialised terminology, limited annotated clinical data, and multilingual use ca
arXiv:2608.18486v1 Announce Type: new Abstract: In a Transformer, each layer attends to past tokens only through KV produced at its own depth, despite the presence of deeper representations during aut
arXiv:2510.14000v2 Announce Type: replace Abstract: The growing demand for parking has increased the need for automated parking planning methods that can operate reliably in confined spaces. In restri
arXiv:2608.17923v1 Announce Type: new Abstract: Appendicitis is one of the most common abdominal emergencies worldwide and requires prompt diagnosis and treatment to prevent life-threatening condition
arXiv:2608.17856v1 Announce Type: new Abstract: Tabular prediction is a critical task across numerous applications. The recent success of large language models has sparked various approaches for adapt
arXiv:2608.17935v1 Announce Type: new Abstract: Surgical performance assessment in minimally invasive surgery largely relies on manual expert review, making it time-consuming, subjective, and difficul
arXiv:2608.17942v1 Announce Type: new Abstract: Machine unlearning removes the influence of specific data from a trained model. However, most methods treat the forgotten concept as isolated. In this p
arXiv:2608.17872v1 Announce Type: new Abstract: Many high-performing pathology tile encoders are now foundation models with hundreds of millions to over a billion parameters. Encoding and storing the
arXiv:2511.23119v3 Announce Type: replace Abstract: High-quality main content extraction from web pages is a critical prerequisite for constructing large-scale training corpora. While traditional heur
arXiv:2608.17983v1 Announce Type: cross Abstract: Ultrasound tongue contour segmentation remains challenging under cross-dataset domain shift, where limited annotations, probe variability, and acquisi
arXiv:2601.18899v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-powered Automatic Speech Recognition (ASR) systems achieve strong performance with limited resources by linking a f
arXiv:2608.17381v1 Announce Type: cross Abstract: Biomolecular design underpins applications from molecular recognition to therapeutics and synthetic biology, yet de novo interaction design remains ch
arXiv:2608.17402v1 Announce Type: new Abstract: Vision encoders are a critical component of vision-language models, and scaling their capacity effectively improves performance. However, dense scaling
arXiv:2506.01297v5 Announce Type: replace Abstract: Representation learning of geospatial locations remains a core challenge in achieving general geospatial intelligence, with increasingly diverging p
arXiv:2608.17542v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architectures (JEPAs) learn world models by predicting future embeddings, but the objective admits a trivial solution of a
arXiv:2608.17323v1 Announce Type: cross Abstract: Robotic manipulation policies trained via imitation learning, such as Action Chunking with Transformers (ACT), can achieve strong performance under id