Shieldstral
arXiv:2607.25857v1 Announce Type: new Abstract: We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7imes its size on text s
Knowledge catalogue
arXiv:2607.25857v1 Announce Type: new Abstract: We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7imes its size on text s
arXiv:2607.25219v1 Announce Type: new Abstract: Social navigation has progressed from simplified 2D environments toward a more general vision-based setting, in which a robot needs to achieve socially
arXiv:2607.25337v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs) learn world models by predicting in representation space rather than reconstructing pixels, making them
arXiv:2607.24767v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems have emerged as a powerful process for allowing large language models (LLMs) to retrieve relevant informa
arXiv:2506.21571v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain of Thought (CoT) before producing final responses, offer a promisi
arXiv:2510.04452v3 Announce Type: replace-cross Abstract: Computer use agents (or 'agents') are generative AI that automates actions within user interfaces from user commands. Current research focuses
arXiv:2607.23633v1 Announce Type: cross Abstract: Sky-image irradiance studies often compare forecasting systems in which the image encoder, temporal model, fusion block, target definition, and traini
arXiv:2607.22598v1 Announce Type: cross Abstract: Educational chatbots powered by large language models (LLMs) show promising effects on learning outcomes, yet most systems delegate pedagogical decisi
arXiv:2607.22746v1 Announce Type: cross Abstract: Rapid post-disaster response requires timely, building-level information on whether structures remain intact, are damaged, or are destroyed. Post-even
arXiv:2607.23002v1 Announce Type: cross Abstract: Large language models increasingly write both code and the tests meant to check it; coverage records what ran, not what was verified. We study an adve
arXiv:2607.22824v1 Announce Type: cross Abstract: Comparing CT reconstruction methods fairly is labor-intensive and largely manual, and many benchmarks use idealized data. We ask whether a large langu
arXiv:2607.02271v2 Announce Type: replace Abstract: Vein recognition is a secure biometric technology often constrained by limited annotated data and imaging variations. While data augmentation mitiga
arXiv:2607.22721v1 Announce Type: cross Abstract: Cognitive remediation tasks often require patients to perform structured actions involving object manipulation and sequential reasoning. For patients
arXiv:2607.22898v1 Announce Type: cross Abstract: Large language models (LLMs) generate code from natural-language prompts, yet real-world prompts rarely provide complete specifications. When prompts
arXiv:2607.18985v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents
arXiv:2607.23478v1 Announce Type: cross Abstract: Fully homomorphic encryption (FHE) provides strong cryptographic guarantees for private inference, but deploying transformer models under FHE remains
arXiv:2605.05540v2 Announce Type: replace Abstract: Fast surrogate modeling for high-dimensional physical dynamics requires more than low short-term error: useful models must roll out efficiently whil
arXiv:2607.23344v1 Announce Type: new Abstract: Named Entity Recognition (NER) for low-resource languages such as Marathi remains a challenging task due to limited annotated resources and linguistic c
arXiv:2607.23175v1 Announce Type: cross Abstract: Reducing toxicity is often framed as a global alignment problem, yet perceptions of harmful language are subjective and context-dependent. We present
arXiv:2607.23319v1 Announce Type: new Abstract: Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and pro
arXiv:2607.24160v1 Announce Type: new Abstract: Accurate vegetation-community classification is essential for ecological monitoring, habitat assessment, and evidence-based environmental management in
arXiv:2607.22635v1 Announce Type: new Abstract: Target-oriented dialogue systems have demonstrated strong capabilities in completing user goals through interactive conversations. However, existing stu
arXiv:2607.23258v1 Announce Type: new Abstract: Large-scale calcium imaging has created an opportunity to build foundation-style models for neural population dynamics, but a central question remains u
arXiv:2411.00839v4 Announce Type: replace-cross Abstract: Deep learning has led to tremendous success in computer vision, largely due to Convolutional Neural Networks (CNNs). However, CNNs have been s
arXiv:2607.23482v1 Announce Type: new Abstract: Accurate State-of-Health estimation is essential for safe battery operation and cost-effective maintenance. Although numerous health indicators have bee
arXiv:2607.22539v1 Announce Type: cross Abstract: The Radiotherapy Scheduling Problem (RTSP) involves determining an optimal schedule for patients undergoing radiation treatments, a task that has a ma
arXiv:2607.22642v1 Announce Type: new Abstract: Enterprise coding agents translate natural-language analytical requests into executable code over proprietary APIs, schemas, and metric definitions. Yet
arXiv:2607.24332v1 Announce Type: new Abstract: Common chunking strategies in Retrieval-Augmented Generation (RAG) systems often create redundant chunks. These redundant chunks make the vector databas
arXiv:2602.10381v2 Announce Type: replace Abstract: Childhood malnutrition remains a major public health concern in Nepal and other low-resource settings, while conventional case-finding approaches ar
arXiv:2607.23388v1 Announce Type: cross Abstract: As constrained learning becomes increasingly common, models are trained under explicit feasibility requirements to enforce fairness, safety, robustnes
arXiv:2607.23338v1 Announce Type: new Abstract: Graph compression reduces the computational cost of graph learning, but its effect on signal propagation remains largely underexplored. Existing work ev
arXiv:2607.22761v1 Announce Type: cross Abstract: Resolving Design Rule Violations (DRVs) in layouts entails an iterative loop of geometric edits and verification. We present DRC-Aid, a closed-loop ag
arXiv:2607.24126v1 Announce Type: cross Abstract: Brain-machine interfaces provide a link between neural activity and external devices, enabling restoration of motor function and advancing human-machi
arXiv:2512.07246v2 Announce Type: replace Abstract: Error detection (ED), which aims to identify incorrect or inconsistent cell values in tabular data, is important for ensuring data quality. Recent s
arXiv:2603.00408v2 Announce Type: replace-cross Abstract: We present an Ising-compatible framework for formal neural-network robustness verification under bounded input perturbations. For piecewise-li
arXiv:2607.22569v1 Announce Type: new Abstract: Coding agents are increasingly integrated into system operations, where their tool use can directly modify project artifacts, execution environments, an
arXiv:2607.22785v1 Announce Type: cross Abstract: Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be acce
arXiv:2607.22959v1 Announce Type: cross Abstract: AI-generated video is increasingly used across marketing, product storytelling, and creative workflows, yet automated; high-precision quality control
arXiv:2607.22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks. While prior work suggests that task adaptation can alter a mode
arXiv:2607.22902v1 Announce Type: new Abstract: Creating sprint backlogs requires considerable effort, as items such as epics, user stories, and tasks can be missed or inconsistently specified. We pro
arXiv:2607.23242v1 Announce Type: new Abstract: Large Language Models (LLMs) have transformed conversational AI, yet high-quality multilingual code-mixed dialogue resources remain scarce, particularly
arXiv:2607.24213v1 Announce Type: new Abstract: Integrating heterogeneous industrial knowledge, including factual relations and decision constraints, remains a core challenge in industrial information
arXiv:2607.22780v1 Announce Type: cross Abstract: Faithful inverse rendering requires visibility and indirect radiance to explain secondary illumination and inter-reflection, yet rasterization-oriente
arXiv:2607.22783v1 Announce Type: cross Abstract: Recent advances in conventional and learning-based image coding have increased the demand for benchmark datasets that support fine-grained assessment
arXiv:2607.24653v1 Announce Type: new Abstract: We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token
arXiv:2607.23545v1 Announce Type: new Abstract: Instruction hierarchy (IH) requires models to prioritize instructions by source, ensuring that higher-priority instructions override lower-priority ones
arXiv:2507.05515v4 Announce Type: replace Abstract: Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grai
arXiv:2411.00918v5 Announce Type: replace-cross Abstract: Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as
arXiv:2607.24072v1 Announce Type: new Abstract: This paper presents an empirical comparison of lexicon-based and Large Language Model (LLM)-based sentiment analysis for extracting market-relevant sign
arXiv:2509.03059v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforceme
arXiv:2607.23204v1 Announce Type: cross Abstract: Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fi
arXiv:2607.22707v1 Announce Type: new Abstract: Single-image reflection removal aims to recover a clean transmission layer from one image captured through glass. We study an explicit decomposition pip
arXiv:2607.15166v2 Announce Type: replace Abstract: Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? W
arXiv:2607.22984v1 Announce Type: cross Abstract: Machine learning models for clinical prediction tasks, such as in-hospital mortality and sepsis onset, routinely achieve high AUROC scores. However, A
arXiv:2607.23532v1 Announce Type: cross Abstract: Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested e
arXiv:2607.23982v1 Announce Type: cross Abstract: Cooperation can fail when socially valuable effort is costly, weakly observable, and mainly benefits others. Drawing on Holmstrom's team moral-hazard
arXiv:2607.22706v1 Announce Type: new Abstract: This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in gener
arXiv:2607.22794v1 Announce Type: cross Abstract: Automatic depression detection with deep learning has shown promise but often suffers from limited generalization due to domain shift arising from int
arXiv:2607.23481v1 Announce Type: new Abstract: This paper presents Mwando, a virtual educational assistant designed to support the teaching and preservation of shiKomori, the language of the Comoros
arXiv:2607.22280v2 Announce Type: replace-cross Abstract: Compressible multiphase flows involving shocks and material interfaces arise in applications such as bubble collapse and droplet breakup, wher