Knowledge catalogue
arXiv:2605.04772v1 Announce Type: new Abstract: Access to diverse, well-annotated medical images with interactive learning tools is fundamental for training practitioners in medicine and related field
arXiv:2605.03482v1 Announce Type: cross Abstract: Persistent external memory enables LLM agents to maintain context across sessions, yet its security properties remain formally uncharacterized. We for
arXiv:2605.03701v1 Announce Type: new Abstract: Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Larg
A preview of Pinecone Nexus, a data retrieval engine available through an early access program, uses the declarative KnowQL language to improve accuracy while reducing token consumption by up to 90%.
arXiv:2508.12778v2 Announce Type: replace Abstract: Medical large vision-language Models (Med-LVLMs) have shown promise in clinical applications but suffer from factual inaccuracies and unreliable out
arXiv:2605.01429v1 Announce Type: cross Abstract: Libraries of Low-Rank Adaptation (LoRA) adapters are becoming a practical by-product of parameter-efficient adaptation. Once such adapters accumulate,
arXiv:2604.25489v1 Announce Type: cross Abstract: Coherent transition radiation (CTR) spectroscopy is a critical diagnostic for characterizing the longitudinal structure of relativistic electron bunch
arXiv:2603.16877v2 Announce Type: replace Abstract: Financial analysts face significant challenges extracting information from lengthy 10-K reports, which often exceed 100 pages. This paper presents a
arXiv:2604.23195v1 Announce Type: cross Abstract: Analog circuit design relies heavily on reusing existing intellectual property (IP), yet searching across heterogeneous representations such as SPICE
arXiv:2604.23801v1 Announce Type: new Abstract: Practitioners deploying small open-weight large language models (LLMs) for medical question answering face a recurring design choice: invest in a domain
arXiv:2604.22180v1 Announce Type: cross Abstract: Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in infor
arXiv:2604.20848v1 Announce Type: cross Abstract: Large Language Model (LLM)-based recommendation systems have demonstrated remarkable capabilities in understanding user preferences and generating per
arXiv:2604.19386v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) has attracted significant attention due to its flexible multimodal query method, yet its development is severely constrai
arXiv:2604.19432v1 Announce Type: new Abstract: Vision foundation models have shown great promise for open-set 3D object retrieval (3DOR) through efficient adaptation to multi-view images. Leveraging
arXiv:2604.17889v1 Announce Type: new Abstract: Despite recent progress in multimodal large language models (MLLMs), reliable visual question answering in aerial scenes remains challenging. In such sc
arXiv:2604.17301v1 Announce Type: new Abstract: Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most
arXiv:2503.22171v2 Announce Type: replace Abstract: Data plays a pivotal role in Text-Based Person Retrieval (TBPR) research. Mainstream research paradigm necessitates real-world person images with ma
arXiv:2604.15628v1 Announce Type: cross Abstract: Cross-modal retrieval between food images and recipe texts is an important task with applications in nutritional management, dietary logging, and cook
arXiv:2604.13721v1 Announce Type: cross Abstract: The technical support team of a supercomputing centre accumulates, over the course of decades, a large volume of resolved incidents that constitute cr
arXiv:2604.14885v1 Announce Type: new Abstract: Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigate
Its noticeable how much of the whole practice of working with AI - the prompts, the skill files, the connectors, retrieval work, the markdown files, etc. - is a substitute for the real problem of cont
arXiv:2604.13418v1 Announce Type: new Abstract: Motivated by the underspecified, multi-hop nature of search queries and the multimodal, heterogeneous, and often conflicting nature of real-world web re
arXiv:2604.12928v1 Announce Type: new Abstract: Speech-to-speech language models have recently emerged to enhance the naturalness of conversational AI. In particular, full-duplex models are distinguis
arXiv:2604.11095v1 Announce Type: cross Abstract: Adapting decoder-only multimodal large language models (MLLMs) for unified multimodal retrieval faces two structural gaps. First, existing methods rel
arXiv:2604.10665v1 Announce Type: new Abstract: HeceTokenizer is a syllable-based tokenizer for Turkish that exploits the deterministic six-pattern phonological structure of the language to construct
arXiv:2604.06616v1 Announce Type: cross Abstract: Hybrid queries combining high-dimensional vector similarity search with spatio-temporal filters are increasingly critical for modern retrieval-augment
arXiv:2610.19830v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) investigators who monitor dark web marketplaces for leaked credentials and breach listings must pass the diverse CAPTC
arXiv:2610.19165v1 Announce Type: cross Abstract: Many real-world questions demand not a single fact but an organized collection of them, yet existing factual knowledge benchmarks almost exclusively t
arXiv:2610.15033v1 Announce Type: cross Abstract: Generative search engines such as ChatGPT, Gemini and Perplexity now decide which Web pages users see as sources, and a growing industry of generative
arXiv:2610.11526v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) offer an energy-efficient computing paradigm through sparse event-driven computation, showing great potential for effic
arXiv:2610.12185v1 Announce Type: new Abstract: Reliable robotic manipulation requires timely intervention to correct emerging deviations and restore progress after execution errors. However, recovery
arXiv:2610.08200v1 Announce Type: new Abstract: We ask whether specific attention heads, and more finely specific neurons inside those heads, are responsible for recognizing that a language model's co
arXiv:2510.16444v2 Announce Type: replace Abstract: Who is being described, where are they, and what are they doing? Referring Atomic Video Action Recognition (RAVAR) answers these questions jointly b
arXiv:2610.03858v1 Announce Type: new Abstract: We investigate a general-purpose layer for deep learning that, instead of compressing arbitrary-size training data into fixed-size weight matrices, stor
arXiv:2609.39938v1 Announce Type: cross Abstract: Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, wherea
arXiv:2609.36406v1 Announce Type: new Abstract: Cell Painting is a high-content morphological profiling assay widely used for phenotype-based biological inference, with mechanism of action (MOA) predi
arXiv:2609.37911v1 Announce Type: cross Abstract: Scientific queries are often brief, while relevant papers use specialized vocabulary. Generated query expansion can bridge this mismatch, but earlier
arXiv:2609.31888v1 Announce Type: cross Abstract: X-ray diffraction (XRD) is a experimental technique for determining the phase composition and structure of crystalline materials. However, interpretin
arXiv:2609.35086v1 Announce Type: new Abstract: In this work, we study portfolio optimization under the stochastic discount factor (SDF) framework by learning market state representations that capture
arXiv:2609.30205v1 Announce Type: new Abstract: Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how cli
arXiv:2609.29519v1 Announce Type: new Abstract: Mental health disorders affect hundreds of millions of people around the world, yet access to professional counseling remains severely limited. AI-power
arXiv:2609.29075v1 Announce Type: new Abstract: Cancer registrars, including Oncology Data Specialists (ODSs), must interpret complex and frequently updated coding and staging standards. We developed
arXiv:2609.28727v1 Announce Type: new Abstract: Contextual biasing improves rare-word recognition in speech large language models (SpeechLLMs), but efficiently exploiting large bias lists remains chal
arXiv:2609.28437v1 Announce Type: new Abstract: Online information is increasingly consumed in video format. Much of this comes in the form of *raw video*: continuous footage taken on a cell phone, wi
arXiv:2609.27526v1 Announce Type: new Abstract: Long-horizon navigation requires an agent to revise its intermediate objectives as evidence accumulates. Full visual histories are costly to process, wh
arXiv:2609.22705v1 Announce Type: new Abstract: Online discourse about urban issues - walkability, cycling infrastructure, public transit, housing density, and street safety - is voluminous but unstru
arXiv:2609.22171v1 Announce Type: new Abstract: Precision healthcare, particularly for conditions like hypertension and cardiovascular disease, necessitates monitoring of dietary sodium intake. Howeve
arXiv:2609.22259v1 Announce Type: new Abstract: Context layers, curated documentation that an analytics agent fetches at query time, produce large accuracy gains on text-to-SQL benchmarks. A with/with
arXiv:2609.21543v1 Announce Type: new Abstract: Does a general vision--language model acquire specialized OCR ability by developing a new reading circuit or by reusing an existing mechanism? We addres
arXiv:2609.19523v1 Announce Type: new Abstract: Web agents often revisit the same sites, yet most evaluations discard the procedures learned in earlier successful interactions. We introduce EconSkills
arXiv:2609.18672v1 Announce Type: new Abstract: An AI assistant that calls tools makes two decisions on every request: which tool to invoke, and whether any available tool applies. In the usual design
arXiv:2609.16591v1 Announce Type: new Abstract: Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual encoder is trained first, followed
arXiv:2609.14572v1 Announce Type: cross Abstract: Teaching abstract theoretical computer science (TCS) concepts such as algorithm analysis and complexity theory is challenging because students must ha
arXiv:2507.19738v2 Announce Type: replace Abstract: While accurate LiDAR depth has been shown to improve stereo matching, high-end LiDAR remains costly and difficult to deploy at scale, motivating gui
arXiv:2609.13851v1 Announce Type: cross Abstract: Post-training vision-language-action (VLA) models for specific robots and tasks requires in-domain demonstrations, yet collecting diverse robot data i
arXiv:2609.14762v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy risk
arXiv:2609.08599v1 Announce Type: new Abstract: Large Language Model (LLM) agents are evolving from single-session tools toward long-term personal assistants that must adapt to individual users across
arXiv:2609.02731v1 Announce Type: cross Abstract: Large vision-language models have achieved remarkable success in vision-language tasks. However, they remain prone to Visual Hallucinations (VHs), und
arXiv:2608.31094v1 Announce Type: new Abstract: Patient identity errors can compromise longitudinal medical records, research databases, and downstream clinical decisions. We present a retinal biometr
arXiv:2608.28155v1 Announce Type: new Abstract: Professional financial examinations require models to combine domain knowledge, calculation, and judgment, yet no benchmark covers the full CFA and FRM