Knowledge catalogue
arXiv:2608.08721v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by drafting multiple tokens for parallel verification, with efficiency critically dete
arXiv:2608.09152v1 Announce Type: new Abstract: Traditional Text-based Person Search (TPS) is typically limited to matching static appearance attributes, severely neglecting dynamic action information
arXiv:2608.09307v1 Announce Type: new Abstract: We present a linearized form of 2-simplicial attention by rewriting the trilinear score as an inner product between a composite query and a key, so that
arXiv:2608.09421v1 Announce Type: cross Abstract: Wearable human activity recognition (HAR) remains challenging due to the computational and energy constraints of deep learning models on resource-limi
arXiv:2608.07894v1 Announce Type: new Abstract: Recent advances have highlighted the potential of machine learning, particularly Large Language Models (LLMs), for analyzing and optimizing programs. We
arXiv:2608.09870v1 Announce Type: cross Abstract: Uniform stability is a classical tool for controlling the generalization error of a learning algorithm. Bousquet, Klochkov, and Zhivotovskiy (2020) sh
arXiv:2608.09723v1 Announce Type: new Abstract: Recent graphical user interface (GUI) grounders have significantly advanced single-shot accuracy on standard benchmarks, yet their performance degrades
arXiv:2607.16305v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding. However, scaling dense or sparse Mixture-of-Experts (
arXiv:2608.09633v1 Announce Type: new Abstract: Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks. While PAD methods achieve strong performance with
arXiv:2608.08698v1 Announce Type: new Abstract: Video token communication represents video content as discrete tokens that differ in their importance to reconstruction and exhibit temporal dependencie
arXiv:2410.15521v2 Announce Type: replace-cross Abstract: We introduce an all-optical system, termed the 'lying mirror', to hide input information by transforming it into misleading, ordinary-looking
arXiv:2410.10523v3 Announce Type: replace-cross Abstract: The aim of this book is to demonstrate the potential for ideas in machine learning to impact on the fields of inverse problems and data assimi
arXiv:2608.07852v1 Announce Type: new Abstract: How a language model internally represents who is speaking, the Assistant, an assigned roleplay persona, or a narrated story character, remains underexp
arXiv:2403.10232v2 Announce Type: replace-cross Abstract: Conventional matrix completion methods approximate the missing values by assuming the matrix to be low-rank, which leads to a linear approxima
arXiv:2608.09588v1 Announce Type: new Abstract: Traditional Text-to-SQL research and benchmarks assume a known target database, overlooking settings in which a query must be routed within a large, het
arXiv:2608.08730v1 Announce Type: new Abstract: Large Language Models are deployed to multiple types of environments, from internet browsers to edge devices, and WebGPU serves as a modern cross-platfo
arXiv:2512.01045v2 Announce Type: replace Abstract: Data-intensive artificial intelligence applications increasingly rely on large-scale, high-quality, explainable, and reproducible datasets, yet the
arXiv:2608.08300v1 Announce Type: new Abstract: Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions. However, when stored user informati
arXiv:2608.09468v1 Announce Type: cross Abstract: State Space Models (SSMs), as a mainstream research direction of linear Transformers, aim to achieve higher efficiency than standard Transformers in l
arXiv:2508.16509v3 Announce Type: replace-cross Abstract: The ability to quantify information transmission is crucial for the analysis and design of both natural and engineered systems. For systems dr
arXiv:2510.19366v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) scales model capacity through sparse activation, and is becoming an important architecture for large language models (LLMs)
arXiv:2608.09764v1 Announce Type: cross Abstract: Transformer-based neural operators have achieved substantial progress in solving Partial Differential Equations (PDEs) by projecting spatial observati
arXiv:2608.09398v1 Announce Type: cross Abstract: Process discovery is one of the central challenges in process mining. Petri nets are particularly attractive because simple local constructs can expre
arXiv:2608.08323v1 Announce Type: new Abstract: Safe robot navigation in crowded spaces requires planning that accounts for where people will be, not only where they are now. Model Predictive Path Int
arXiv:2608.08819v1 Announce Type: new Abstract: Objective. MRI provides excellent soft-tissue contrast, but long acquisition times can cause patient discomfort and lead to motion artifacts, forcing a
arXiv:2608.08704v1 Announce Type: cross Abstract: Kernel spectral clustering with a single bandwidth can be inadequate for data exhibiting multiple characteristic pairwise-distance scales, a problem p
arXiv:2608.08772v1 Announce Type: new Abstract: Emotion is central to human communication, and its expression varies across languages. Large audio-language models (LALMs) achieve strong performance on
arXiv:2608.07574v1 Announce Type: new Abstract: Skin lesion classification plays an important role in supporting the early diagnosis of skin cancer. However, automated analysis remains challenging due
arXiv:2608.09035v1 Announce Type: cross Abstract: Text-to-music generation has advanced rapidly, but current systems still rely primarily on global text prompts, leaving the structural organization of
arXiv:2608.07559v1 Announce Type: new Abstract: In 3D reconstruction, mirrors introduce significant challenges by creating distorted and fragmented spaces, resulting in inaccurate and unreliable 3D mo
arXiv:2608.08107v1 Announce Type: cross Abstract: Multimodal expansion of large language models (LLMs) enables new perceptual capabilities but often compromises the language intelligence acquired duri
arXiv:2507.03094v2 Announce Type: replace Abstract: Many challenges in scientific imaging involve solving ill-posed inverse problems, where the goal is to recover spatio-temporal fields from indirect,
arXiv:2505.08610v2 Announce Type: replace-cross Abstract: Nowadays, Neural Networks are considered one of the most effective methods for various tasks such as anomaly detection, computer-aided disease
arXiv:2608.07598v1 Announce Type: new Abstract: Animating objects in a static 3D Gaussian scene requires an explicit object-level dynamic state and a controllable model of object motion. Existing dyna
arXiv:2608.09602v1 Announce Type: new Abstract: Strictures caused by esophageal cancer can narrow down the esophageal lumen, leading to dysphagia. Palliation of dysphagia has driven the development of
arXiv:2604.02979v2 Announce Type: replace Abstract: Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing tra
arXiv:2601.19040v2 Announce Type: replace Abstract: Time Series Foundation Models (TSFMs) are a powerful paradigm for time series analysis and are often enhanced by synthetic data augmentation to impr
arXiv:2608.08696v1 Announce Type: new Abstract: 3D occupancy prediction is fundamental to scene understanding, yet existing 3D semantic occupancy methods are typically specialized to fixed scene types
arXiv:2502.11027v5 Announce Type: replace Abstract: Large language model (LLM) scaling inference is key to unlocking greater performance, and leveraging diversity has proven an effective way to enhanc
arXiv:2505.00110v2 Announce Type: replace-cross Abstract: We show that deep Heaviside networks (DHNs) have limited expressiveness but that this can be overcome by including either skip connections or
arXiv:2608.08266v1 Announce Type: cross Abstract: Code generated by modern language models often reads naturally. Yet, it also often fails to implement what was asked. This should be no surprise, as r
arXiv:2608.09403v1 Announce Type: new Abstract: Whole slide images (WSIs) in digital histopathology are acquired at discrete magnification levels encoding complementary diagnostic information from glo
arXiv:2608.09218v1 Announce Type: new Abstract: Score-driven filters multiply a scaled log-likelihood score by a gain that controls the update magnitude. We treat this gain as a decision variable and
arXiv:2608.08308v1 Announce Type: cross Abstract: Modern vision systems must operate in 'open-world' settings, where models must recognize known categories and detect unseen or anomalous content. Conv
arXiv:2608.08265v1 Announce Type: new Abstract: Oracle routing measures how much a pool of language models could gain from per-query selection, but the diagnostic has two flaws: testing against a best
arXiv:2608.08416v1 Announce Type: new Abstract: Probably Approximately Correct (PAC) learning [Val84] is a fundamental learning model that has been extensively investigated. In this model, H subseteq
arXiv:2505.06589v3 Announce Type: replace-cross Abstract: Modern machine learning repeatedly manipulates probability measures: empirical datasets, generated samples, latent distributions, class-condit
arXiv:2608.09914v1 Announce Type: cross Abstract: Hardware assurance relies on scanning electron microscopy (SEM) to verify nanoscale structures, but assembling the large, high-quality datasets requir
arXiv:2608.08368v1 Announce Type: new Abstract: Diabetic retinopathy (DR) remains a leading cause of vision loss among working-age adults worldwide, making reliable severity grading clinically importa
arXiv:2608.08753v1 Announce Type: new Abstract: Alzheimer's disease (AD) progression is a longitudinal process with subtle pathological cues in the early stages. Yet, computational constraints have li
arXiv:2608.09223v1 Announce Type: new Abstract: AI-generated image detectors generalize poorly when their training and test images originate from different generators or datasets. Despite the rich spa
arXiv:2608.08078v1 Announce Type: new Abstract: Interval prediction aims to achieve a target coverage level while producing intervals that are as short as possible. Many conformal regression pipelines
arXiv:2608.07999v1 Announce Type: new Abstract: AI-generated image (AIGI) detection has become increasingly challenging due to the rapid advancement of generative models and the diminishing gap betwee
arXiv:2608.08773v1 Announce Type: new Abstract: Long-horizon multi-part object disassembly requires robots to compute feasible sequences of collision-free removal motions, even in the presence of tigh
arXiv:2608.09721v1 Announce Type: new Abstract: Lung cancer remains one of the leading causes of cancer- related mortality worldwide. Although targeted therapies have improved outcomes for patients wi
arXiv:2608.08053v1 Announce Type: cross Abstract: Simulation-ready 3D assets are central to robotics and embodied AI. Generating them from a single image is usually framed as a vision-language model t
arXiv:2603.07066v2 Announce Type: replace-cross Abstract: Generative diffusion models are increasingly used for medical imaging data augmentation, but text prompting cannot produce causal training dat
arXiv:2608.07475v1 Announce Type: cross Abstract: Generative Artificial Intelligence (GenAI) presents a governance challenge for STEM assessment. Unrestricted access can enable task outsourcing that u
arXiv:2608.07478v1 Announce Type: cross Abstract: India's 22 official languages create a critical accessibility barrier: the majority of medical documentation exists exclusively in English, yet the pa
arXiv:2602.18093v2 Announce Type: replace Abstract: Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising p