Knowledge catalogue
arXiv:2603.12617v2 Announce Type: replace-cross Abstract: Speculative decoding has emerged as a widely adopted paradigm for accelerating large language model inference, where a lightweight draft model
arXiv:2608.05576v1 Announce Type: new Abstract: When a large language model (LLM) writes Harry Potter fanfiction, it reliably produces fundamental elements of the Hogwarts universe, such as recognizab
arXiv:2608.05423v1 Announce Type: cross Abstract: In generative training, a model produces an output and is penalised for its difference from an example. With one output per comparison, a model that p
arXiv:2608.04710v1 Announce Type: cross Abstract: Integrated Sensing and Communication (ISAC) combines sensing and communication to efficiently utilize wireless resources and is emerging as a key para
arXiv:2608.04180v1 Announce Type: new Abstract: Feature selection is a critical step in electronic health record (EHR)-based predictive modeling, where input variables are often high-dimensional, spar
arXiv:2608.04945v1 Announce Type: cross Abstract: The emergence of the ISO standard GQL introduces a powerful query language extending first-order logic with controlled recursion, raising the question
arXiv:2608.04944v1 Announce Type: cross Abstract: We propose a deep learning framework for image restoration from images degraded by both multiplicative Gamma noise and blur. Unlike conventional deep
arXiv:2608.04012v1 Announce Type: new Abstract: Artificial intelligence systems are increasingly expected to operate over repeated cycles of interaction, adaptation, and update rather than through iso
arXiv:2512.21113v2 Announce Type: replace Abstract: Transformers are increasingly adopted for modeling and forecasting time-series, yet their internal mechanisms remain poorly understood from a dynami
arXiv:2608.04548v1 Announce Type: cross Abstract: Multimodal large language model (MLLM) unlearning methods have been proposed to remove private, sensitive, or proprietary information from well-traine
arXiv:2608.04808v1 Announce Type: new Abstract: Part-of-speech tagging for low-resource languages remains challenging due to limited annotated data, especially for linguistically complex languages. Ga
arXiv:2608.04025v1 Announce Type: cross Abstract: Whole-slide survival models commonly provide risk rankings without calibrated statements about individual event times. We evaluate fixed-cutoff drcosa
arXiv:2608.04704v1 Announce Type: new Abstract: Reliable environment monitoring is essential for the safe and efficient operation of automated railway systems, covering all Grades of Automation (GoA),
arXiv:2608.04026v1 Announce Type: cross Abstract: In this paper, we develop a trust-region framework for understanding the behavior of adaptive moment estimation mechanisms, such as extsc{Adam}, in st
arXiv:2608.05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. Ho
arXiv:2608.04502v1 Announce Type: cross Abstract: Attention--Feed-Forward Network (FFN) Disaggregation (AFD) is emerging as a promising architecture for serving Mixture-of-Experts (MoE) language model
arXiv:2608.04618v1 Announce Type: new Abstract: Heterogeneous language-model ensembles expand the space of candidate responses, yet they lack a principled criterion for when a newly generated answer s
arXiv:2608.04016v1 Announce Type: cross Abstract: Social disadvantage is associated with multimorbidity, but the pathways linking social conditions to disease burden remain poorly understood. We devel
arXiv:2603.02371v2 Announce Type: replace Abstract: Automated analysis of articulated bodies is crucial in medical imaging. Existing surface-based models often ignore internal volumetric structures an
arXiv:2608.04329v1 Announce Type: new Abstract: Seam carving is a classical content-aware image resizing operator that modifies the width or height of an image by repeatedly removing (or inserting) se
arXiv:2608.04310v1 Announce Type: new Abstract: The Rashomon effect describes the phenomenon that many models can achieve nearly equivalent performance on the same learning task, with significant rami
arXiv:2608.04753v1 Announce Type: new Abstract: Attention layers are the backbone of today's most powerful and impactful models. Models with multi-million and billion parameters rely on contextual kno
arXiv:2608.04243v1 Announce Type: new Abstract: Multi-head attention layers produce vector representations that support multiple downstream tasks. We establish bounds on the number of heads required i
arXiv:2606.14591v2 Announce Type: replace-cross Abstract: Recent advances in pretrained large audio-language models (LALMs) have demonstrated strong capabilities across speech, sound, and music. To ad
arXiv:2608.05074v1 Announce Type: new Abstract: Spatial mapping of lung adenocarcinoma (LUAD) growth patterns across whole slide images (WSIs) requires resolving architectural context at the region le
arXiv:2512.03590v3 Announce Type: replace Abstract: Existing talking-head generation methods primarily target open-ended generation rather than bridging two existing video segments. In this paper, we
arXiv:2608.04454v1 Announce Type: new Abstract: Mixture-of-experts vision-language models (MoE-VLMs) increase model capacity with sparse expert activation, yet deployment requires storing the full exp
arXiv:2608.05066v1 Announce Type: new Abstract: In 3D reconstruction, camera calibration is an essential element for achieving high fidelity and accuracy of the reconstructed geometry. While existing
arXiv:2608.04047v1 Announce Type: cross Abstract: Conventional BB84 Quantum Key Distribution (QKD) systems rely on a fixed 11% Quantum Bit Error Rate (QBER) threshold to detect eavesdropping. However,
arXiv:2608.05025v1 Announce Type: new Abstract: Joint Energy-Based Models (JEM) unify classification and generation within a single network and support out-of-distribution (OOD) detection. Canonical J
arXiv:2608.05085v1 Announce Type: cross Abstract: Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to
arXiv:2608.04515v1 Announce Type: cross Abstract: Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thou
arXiv:2511.19418v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual per
arXiv:2608.05124v1 Announce Type: cross Abstract: Long context reasoning in large language models (LLMs) is usually constrained by the fact that a single inference trajectory has to simultaneously exp
arXiv:2608.04559v1 Announce Type: new Abstract: Although deep neural network-based remote sensing object detectors have achieved strong performance, they remain vulnerable to adversarial perturbations
arXiv:2608.04336v1 Announce Type: cross Abstract: Code generation systems make each LLM call with a model, a prompt, and decoding settings. However, existing optimization methods usually tune only par
arXiv:2608.04926v1 Announce Type: cross Abstract: As chart images, tabular data, and visualization code play increasingly important roles across diverse domains, cross-representation understanding acr
arXiv:2511.09002v3 Announce Type: replace-cross Abstract: Self-consuming generative models have received significant attention over the last few years. In this paper, we study a self-consuming generat
arXiv:2608.04333v1 Announce Type: new Abstract: Large language model (LLM) configuration evaluation is challenging due to limited evaluation budgets, varying costs, and multiple competing objectives.
arXiv:2608.04655v1 Announce Type: cross Abstract: Curvilinear structure analysis is an important and fundamental task in multimedia. However, the controllable generation of images with precise curvili
arXiv:2608.04444v1 Announce Type: cross Abstract: Large language models (LLMs) often generate inaccurate answers due to their reliance on static internal knowledge. Retrieval-augmented generation (RAG
arXiv:2608.05120v1 Announce Type: new Abstract: Kinetic model discovery is a central challenge in chemical engineering, as accurate rate expressions are essential for understanding and controlling che
Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to complex questions such a
arXiv:2608.04477v1 Announce Type: cross Abstract: Cloud-based language model services routinely process prompts containing sensitive information. Obfuscation-based defenses---including ObfusLM, Sentin
arXiv:2608.04428v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have emerged as a key component in embodied AI. Among existing approaches, diffusion-based VLA models achieve supe
arXiv:2608.04702v1 Announce Type: cross Abstract: Benchmarking deep learning (DL) models for multi-label classification (MLC) of remote sensing images (RSI) typically yields rankings that do not gener
arXiv:2608.04531v1 Announce Type: new Abstract: Functional flow matching is posed on distributions of functions but implemented from finitely many coefficients or point values. Under scattered or adap
arXiv:2608.04652v1 Announce Type: cross Abstract: Image mixup is a widely adopted data augmentation strategy, yet it is ill-suited for ordinal classification tasks such as medical disease grading, whe
arXiv:2601.20985v2 Announce Type: replace Abstract: Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory s
arXiv:2608.04496v1 Announce Type: new Abstract: Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottl
arXiv:2608.04847v1 Announce Type: new Abstract: Despite its cultural relevance and diffusion, queer slang remains underrepresented in Natural Language Processing research. Towards addressing this gap,
arXiv:2604.00209v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in high-stakes settings, yet they frequently violate contextual privacy by disclosing private
arXiv:2604.05087v3 Announce Type: replace Abstract: Document expansion is a classical technique for improving retrieval quality, and is attractive since it shifts computation offline, avoiding additio
arXiv:2608.04928v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning offers a window into the decision-making of large language models (LLMs), which can be monitored for target behaviors b
arXiv:2511.17354v4 Announce Type: replace Abstract: Recent advances in self-supervised visual representation learning have demonstrated the effectiveness of predictive latent-space objectives for lear
arXiv:2608.04252v1 Announce Type: cross Abstract: The dynamical Lie algebraic (DLA) theory of variational quantum algorithms (VQAs) predicts commonplace exponentially vanishing loss and gradient varia
arXiv:2405.18220v4 Announce Type: replace-cross Abstract: Tensor-based discrete density estimation requires flexible modeling and proper divergence criteria to enable effective learning; however, trad
arXiv:2608.04278v1 Announce Type: cross Abstract: Coding agents increasingly work across sessions, but prose notes can preserve a conclusion without the program state that supported it. After an upstr
arXiv:2608.04390v1 Announce Type: new Abstract: Large language models (LLMs) perform table-centric prediction through in-context learning, making demonstration selection critical to performance. Exist
arXiv:2608.04401v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models enable model scaling while maintaining low inference-time compute by activating only a subset of experts per token. Howe