Knowledge catalogue
arXiv:2603.04795v2 Announce Type: replace-cross Abstract: Medical image analysis depends on accurate segmentation and controllable synthesis, but both tasks face severe spatial imbalance: lesions occu
arXiv:2607.04819v1 Announce Type: new Abstract: Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequentia
arXiv:2607.03204v1 Announce Type: new Abstract: In this study, we propose a layout-independent control allocator capable of zero-shot deployment across diverse actuator configurations. The proposed me
arXiv:2607.04270v1 Announce Type: cross Abstract: Large language models (LLMs) have recently emerged as powerful backbones for recommender systems by reformulating recommendation as a token-level gene
arXiv:2607.03320v1 Announce Type: new Abstract: Remote sensing image change captioning (RSICC) generates natural-language descriptions of semantic changes between paired remote sensing images (RSIs),
arXiv:2607.04603v1 Announce Type: cross Abstract: Infrared small target detection (IRSTD) aims to identify long distance small targets from complex infrared backgrounds, and is a fundamental task in r
arXiv:2607.02549v1 Announce Type: new Abstract: Many manipulation tasks require reasoning about free-space affordances: discovering volumes where an extended rigid tool can safely navigate, complement
arXiv:2607.04643v1 Announce Type: new Abstract: Video quality assessment (VQA) plays a critical role in optimizing video delivery systems. While numerous objective metrics have been proposed to approx
arXiv:2607.03481v1 Announce Type: new Abstract: Modernizing cancer registries with deep learning is opening new opportunities to automate labor-intensive tasks such as the coding of pathology reports.
arXiv:2602.10099v2 Announce Type: replace-cross Abstract: Leveraging representation encoders for generative modeling offers a path for efficient, high-fidelity synthesis. However, standard diffusion t
arXiv:2607.05300v1 Announce Type: new Abstract: Parameter-efficient fine-tuning still leaves a broad space of behavior-changing updates reachable, so a poisoned objective can be represented and optimi
arXiv:2607.05263v1 Announce Type: new Abstract: This paper concerns the problem of unsupervised temporal action segmentation for long, untrimmed videos. Recent successful approaches follow a joint rep
arXiv:2607.04711v1 Announce Type: new Abstract: Continual learning aims to progressively learn from a sequence of tasks, each containing a disjoint subset of classes, while preserving previously learn
arXiv:2406.14340v2 Announce Type: replace-cross Abstract: The standard stochastic gradient descent (SGD) optimization method, as well as adaptive methods such as the Adam optimizer fail to converge if
arXiv:2607.04638v1 Announce Type: new Abstract: Referring expression comprehension (REC) aims to localize the object in an image described by natural language. In Weakly supervised REC (WREC), existin
arXiv:2607.04409v1 Announce Type: new Abstract: Learning and planning in imagination using world models provides an effective paradigm for training agents for decision-making. However, existing approa
arXiv:2607.02909v1 Announce Type: cross Abstract: Taxonomies provide key information about the semantic relationships between concepts and the inherent organization of vision and language. Despite the
arXiv:2602.09530v2 Announce Type: replace-cross Abstract: We introduce AutoSpec, a neural network framework for discovering iterative spectral algorithms for large-scale numerical linear algebra and n
arXiv:2511.20446v3 Announce Type: replace Abstract: The way humans interact with each other, including interpersonal distances, spatial configuration, and motion, varies significantly across different
arXiv:2607.03488v1 Announce Type: new Abstract: Text-to-image diffusion models fail to generate correct object counts in dense scenes, where overlapping instances collapse into indistinguishable struc
arXiv:2607.03247v1 Announce Type: new Abstract: Single-Photon Avalanche Diode (SPAD)-based Light Detection and Ranging (LiDAR) is emerging for autonomous vehicles due to its high sensitivity and preci
arXiv:2401.10805v4 Announce Type: replace-cross Abstract: We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in a
arXiv:2603.17484v2 Announce Type: replace Abstract: Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on l
arXiv:2603.00968v2 Announce Type: replace-cross Abstract: The Nash-Sutcliffe efficiency (ext{NSE}) is a widely used, positively oriented relative measure for evaluating forecasts across multiple time
arXiv:2607.04319v1 Announce Type: new Abstract: A companion paper showed that a transformer's feed-forward layer can be rebuilt from explicit fuzzy set operations - intersection, set-difference, and a
arXiv:2607.02829v1 Announce Type: new Abstract: Existing ViT-based weather forecasting models apply uniform computation across all spatial tokens, even though nearby atmospheric grid points often cont
arXiv:2607.04486v1 Announce Type: cross Abstract: Diagnosing and monitoring diseases frequently involves the analysis of human biological samples, with blood analysis being pivotal. Specifically, leuk
arXiv:2506.02212v2 Announce Type: replace-cross Abstract: Natural Language Processing (NLP) has transformed various fields beyond linguistics by applying techniques originally developed for human lang
arXiv:2607.03715v1 Announce Type: new Abstract: Medical imaging models often degrade when deployed at new clinical sites due to differences in imaging equipment, protocols, and patient populations. Te
arXiv:2602.16086v3 Announce Type: replace Abstract: Recent collapse-free quantizers such as FSQ achieve stable training by replacing the learnable codebook with an engineered geometry: a fixed scalar
arXiv:2607.03920v1 Announce Type: new Abstract: Embodied navigation is moving toward long-horizon missions, yet existing long-horizon benchmarks are largely acoustically silent, and audio-visual navig
arXiv:2607.04553v1 Announce Type: cross Abstract: We present a bidirectional framework for estimating the energy consumption of text-to-video (T2V) and text-to-video-audio (T2VA) models from architect
arXiv:2607.04934v1 Announce Type: new Abstract: Automatic sleep staging is a key technology for precise diagnosis and treatment of sleep disorders as well as long-term home sleep monitoring. Portable
arXiv:2607.03062v1 Announce Type: new Abstract: While lightweight polyp segmentation is highly desirable for low-cost deployment, reported performance gains often stem from upgraded backbone encoders,
arXiv:2607.04801v1 Announce Type: new Abstract: Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each s
arXiv:2607.02715v1 Announce Type: new Abstract: Recently, neural operators have shown promising outcomes for learning solution operators of differential equations directly from data. This framework le
arXiv:2603.13334v4 Announce Type: replace-cross Abstract: Lipschitz-based robustness certification bounds a network's sensitivity through concrete numerical computation rather than symbolic reasoning,
arXiv:2604.01641v2 Announce Type: replace Abstract: We introduce LivingWorld, an interactive framework for generating 4D worlds with environmental dynamics from a single image. While recent advances i
arXiv:2607.04412v1 Announce Type: new Abstract: Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. W
arXiv:2607.05391v1 Announce Type: new Abstract: Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we id
arXiv:2508.16181v2 Announce Type: replace-cross Abstract: Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across inde
arXiv:2501.08579v3 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current
arXiv:2607.05031v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to produce test oracles, the part of a test that decides whether observed behavior is correct. Yet
arXiv:2607.04579v1 Announce Type: cross Abstract: CI/CD workflows have become executable operational policy: they decide what gets built, tested, released, and deployed, and they mediate how maintaine
arXiv:2607.03350v1 Announce Type: cross Abstract: Malicious Python packages have become a major threat to software supply chain ecosystems due to the widespread adoption of open-source repositories su
arXiv:2607.04983v1 Announce Type: cross Abstract: This article is about the development of a fuzzy cognitive map using a local large language model. In the light of recent advances it is evident that
arXiv:2607.03651v1 Announce Type: new Abstract: While traditional hub capacity planning models optimize effectively for quantitative inputs, they often fail to digest qualitative business context. We
arXiv:2607.02703v1 Announce Type: cross Abstract: In this paper, we describe LLMoxie, an institutional AI platform whose three-tiered architecture supports multi-cloud and on-premise inference, a Lite
arXiv:2507.11878v5 Announce Type: replace Abstract: LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refu
arXiv:2603.07965v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) for high-dimensional constrained problems remains a significant challenge due to the curse of dimensionality. We pr
arXiv:2506.19136v4 Announce Type: replace Abstract: We show that the out-of-equilibrium driving protocol of score-based generative models (SGMs) can be learned via local learning rules. The gradient w
arXiv:2607.05114v1 Announce Type: cross Abstract: Large Language Models (LLMs) and high-dimensional perception networks increasingly rely on parameter-efficient fine-tuning (PEFT) to adapt to diverse
arXiv:2604.04931v2 Announce Type: replace Abstract: Local feature matching has long been a fundamental component of 3D vision systems such as Structure-from-Motion (SfM), yet progress has lagged behin
arXiv:2607.02924v1 Announce Type: new Abstract: As autonomous vehicles (AVs) operate in increasingly dynamic traffic conditions, lateral control must be performed while longitudinal speed and accelera
arXiv:2607.03751v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models acquire broad embodied capabilities through large-scale pretraining, yet their generalization remains far more fragi
arXiv:2607.03699v1 Announce Type: new Abstract: In many multisensor systems, measurements from different sensors are subject to unknown relative time delays. Accurate state estimation requires that de
arXiv:2607.03072v1 Announce Type: cross Abstract: Simulation is essential for maritime robotics, supporting operator training, mission rehearsal, and human-vehicle interaction in environments where re
arXiv:2607.04733v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain
arXiv:2607.03682v1 Announce Type: cross Abstract: Convection-dominated convection-diffusion problems often develop thin layers, where the solution has sharp transition profiles and its derivatives are
arXiv:2607.02763v1 Announce Type: new Abstract: Spoken Question Answering (SQA) remains largely focused on high-resource languages and carefully recorded speech, limiting the reach of speech-LLM metho