Knowledge catalogue
arXiv:2608.14198v1 Announce Type: cross Abstract: Banks analyse sequential financial transaction data to perform many tasks, including fraud prevention, credit risk assessment and offer personalizatio
We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve compositional reasoning.
arXiv:2603.06201v2 Announce Type: replace Abstract: Skeleton-based temporal action segmentation is a fundamental yet challenging task, playing a crucial role in enabling intelligent systems to perceiv
arXiv:2606.15158v2 Announce Type: replace Abstract: Reference-guided generation (e.g., object compositing, customization) has progressed rapidly, yet current pipelines share a fundamental limitation:
arXiv:2608.14379v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation. However, existing benchmarks mainly evaluate
arXiv:2608.14456v1 Announce Type: new Abstract: Short-horizon forecasting of fine particulate matter (PM2.5) remains difficult when observations from the target domain are limited and the statistical
arXiv:2608.13717v1 Announce Type: new Abstract: Streaming automatic speech recognition (ASR) underperforms on domain-shifted target audio, where labeled in-domain data is costly to prepare while unlab
arXiv:2608.12894v1 Announce Type: new Abstract: Cultural evaluation of large language models (LLMs) often focuses on high-resource standard languages, leaving regional culture and dialect communities
arXiv:2506.17337v5 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings. However, developing sp
arXiv:2608.12944v1 Announce Type: new Abstract: Electrocardiography (ECG), photoplethysmography (PPG), and phonocardiography (PCG) provide complementary views of the same cardiac cycle, yet existing c
arXiv:2608.13524v1 Announce Type: new Abstract: Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters furt
arXiv:2608.13474v1 Announce Type: new Abstract: Vision-language-action models (VLAs) are moving rapidly towards deployment as general-purpose manipulation policies, but we currently lack basic tools f
arXiv:2608.13194v1 Announce Type: new Abstract: We propose a fidelity-constrained framework that anchors the output of a black-box denoiser to its input without retraining and with little additional c
arXiv:2608.12687v1 Announce Type: new Abstract: Bayesian optimization (BO) is a sample-efficient framework for analog circuit topology search, where evaluating each candidate topology can require cost
arXiv:2608.13147v1 Announce Type: new Abstract: Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera streams.
arXiv:2608.12904v1 Announce Type: new Abstract: Clinical intelligence requires estimating a patient's underlying condition from incomplete observations rather than learning isolated mappings from scan
arXiv:2608.13505v1 Announce Type: cross Abstract: Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific t
arXiv:2608.13545v1 Announce Type: cross Abstract: Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as pr
arXiv:2608.12435v1 Announce Type: new Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, howeve
arXiv:2608.13425v1 Announce Type: new Abstract: Self-supervised learning (SSL) speech representations achieve strong performance for Parkinson's disease (PD) detection within individual corpora. Howev
arXiv:2512.17897v2 Announce Type: replace-cross Abstract: We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapt
arXiv:2509.01134v2 Announce Type: replace-cross Abstract: Generative models for high-quality materials are particularly desirable to make 3D content authoring more accessible. However, the majority of
arXiv:2608.13087v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identi
arXiv:2608.13095v1 Announce Type: cross Abstract: Training and evaluating spatial reasoning in embodied agents requires diverse environments that are both geometrically faithful and semantically query
arXiv:2608.13341v1 Announce Type: cross Abstract: Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Convent
arXiv:2509.17449v2 Announce Type: replace Abstract: Queer vernacular is rarely studied in NLP, despite advancements in resources and evaluation for other sociolects and informal language. Because of t
arXiv:2608.13317v1 Announce Type: new Abstract: Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck.
arXiv:2608.12624v1 Announce Type: new Abstract: Structure-preserving machine learning embeds physical structure directly into model architectures, yet uncertainty quantification (UQ) for such hard-con
arXiv:2608.12695v1 Announce Type: new Abstract: Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences. It re
arXiv:2505.02787v3 Announce Type: replace Abstract: Current color fundus image registration approaches are limited, among other things, by the lack of labeled data, which is even more significant in t
arXiv:2608.13556v1 Announce Type: new Abstract: Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures ha
arXiv:2608.12274v1 Announce Type: cross Abstract: Background: Accurate segmentation of the Left Anterior Descending (LAD) artery in 3D free-breathing, non-contrast CT is critical for cardiac dose spar
arXiv:2505.18315v3 Announce Type: replace-cross Abstract: We introduce extbf{CoLoRA} (Convolutional Low-Rank Adaptation), a parameter-efficient fine-tuning method for convolutional neural networks (CN
arXiv:2608.11701v1 Announce Type: cross Abstract: Copying short-term memory (STM) into a slower store can preserve state across a context boundary, but persistence alone does not ensure that the retai
arXiv:2608.12279v1 Announce Type: new Abstract: Test-time adaptation (TTA) aims to enhance the cross-domain performance of pre-trained models by adapting to unlabeled test data. While most existing TT
arXiv:2608.11937v1 Announce Type: new Abstract: Foundation models for time-dependent partial differential equations (PDEs) are trained on large and diverse collections of physical systems and can gene
arXiv:2608.12064v1 Announce Type: new Abstract: We invert the typical formulation of sketch generation: instead of drawing strokes in order, we predict a 2D field that defines the order in which strok
arXiv:2608.11748v1 Announce Type: new Abstract: Hyperspectral pansharpening aims to reconstruct a high resolution hyperspectral (HRHS) image from a panchromatic (PAN) image and a low resolution hypers
arXiv:2608.11605v1 Announce Type: new Abstract: World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves durin
arXiv:2608.11562v1 Announce Type: cross Abstract: Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vision tasks. Although single-image
arXiv:2608.11674v1 Announce Type: cross Abstract: On-policy rollout methods such as GRPO are central to post-training of large language models, yet they frequently suffer from training instabilities,
arXiv:2608.12209v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have achieved remarkable progress, visual understanding and generation are typically treated as divergent
arXiv:2608.11263v1 Announce Type: new Abstract: Cross-modal place recognition (CMPR) aims to identify the same location across heterogeneous sensing modalities, such as vision and LiDAR. Existing meth
arXiv:2512.11839v2 Announce Type: replace Abstract: Designing generalizable control policies that operate reliably under changing conditions is essential for robust network services in modern digital
arXiv:2608.12239v1 Announce Type: cross Abstract: Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hi
arXiv:2608.11574v1 Announce Type: new Abstract: Hand Pose Estimation (HPE) is a fundamental technology for various applications such as AR/VR and robotics. In these applications, the visibility of eac
arXiv:2608.12218v1 Announce Type: cross Abstract: Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories. This
arXiv:2608.11426v1 Announce Type: new Abstract: The lack of diversity in LM content is widely attributed to the alignment process, but how and where exactly in the pipeline this collapse begins is unk
arXiv:2608.11745v1 Announce Type: new Abstract: Pose-driven human animation synthesizes a video of a target person from a single reference image and a driving pose stream. Real-time generation is esse
arXiv:2608.12149v1 Announce Type: new Abstract: We present the first systematic study of Massive activations (MAs) in layer-interleaved HLA LLMs and uncover two architecture-aligned morphologies: MAs
arXiv:2608.12036v1 Announce Type: new Abstract: AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain p
arXiv:2608.11329v1 Announce Type: cross Abstract: A common approach to adding audio to a vision-language model is to train or adapt a large omni-modal system. We show that a lightweight alternative ca
arXiv:2608.12219v1 Announce Type: new Abstract: Treating patients with combinations of drugs reduces the risk of resistance to any individual drug. Finding effective combinations is difficult because
arXiv:2608.11474v1 Announce Type: new Abstract: Object Hallucination in large vision-language models (LVLMs), where models generate non-factual content about input images, remains a critical barrier t
The way most people leverage test-time compute today is via a form of test-time NL reasoning that is computationally equivalent to test-time search (sometimes with a verifier / grader in the loop). Th
arXiv:2608.11752v1 Announce Type: new Abstract: Talking-video character replacement requires coordinated transfer of appearance and voice while preserving the source motion, scene, linguistic content,
arXiv:2608.12276v1 Announce Type: new Abstract: High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative samplin
arXiv:2608.10939v1 Announce Type: cross Abstract: Multilingual short-text classification supports operational systems such as content moderation, customer support routing, and intent recognition, yet
arXiv:2608.10351v1 Announce Type: new Abstract: In this work we present a method to accelerate the optimization of learning high dimensional functions using deep neural network (DNN). This optimizatio
arXiv:2608.11205v1 Announce Type: new Abstract: Frechet distance has recently emerged as an effective distribution-level objective for generator post-training, complementing the conventional sample-le