Knowledge catalogue
arXiv:2610.09892v2 Announce Type: replace-cross Abstract: Feedback from automated testing, human red teaming, and incident response can strengthen an AI system's defenses when discovered failures lead
arXiv:2610.11315v1 Announce Type: cross Abstract: In diffusion transformers, low-rank branches can mitigate 4-bit weight--activation (W4A4) post-training quantization (PTQ) loss by decomposing each we
arXiv:2610.12437v1 Announce Type: cross Abstract: Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view
arXiv:2610.11845v1 Announce Type: new Abstract: Spin in clinical trials includes reporting practices that distort the presentation of results. This is particularly critical in medicine, where spin is
arXiv:2610.12214v1 Announce Type: cross Abstract: Recent full-duplex spoken dialog models enable simultaneous listening and speaking, but fine-grained models still advance their backbone autoregressiv
arXiv:2610.11067v1 Announce Type: new Abstract: Prompt learning is a popular method for adapting foundation models, but learned prompts are typically task-specific and fail to generalize to new classe
arXiv:2610.12052v1 Announce Type: cross Abstract: Despite their empirical success, why diffusion models overcome the bottlenecks of classical score-based samplers remains unclear. In this work, we lev
arXiv:2610.11751v1 Announce Type: new Abstract: Co-denoising pretrained representations such as DINO can substantially improve the training speed and quality of flow matching models, but it introduces
arXiv:2502.20612v2 Announce Type: cross Abstract: In self-supervised contrastive learning, negative pairs are typically constructed using an anchor image and a sample drawn from the entire dataset, ex
arXiv:2610.10865v1 Announce Type: new Abstract: Self-supervised speech encoders contain linguistic and paralinguistic information in a shared, entangled representation space. We combine a TopK sparse
arXiv:2610.11141v1 Announce Type: new Abstract: Relative localization is crucial for a multi-robot system to collaboratively perform tasks, such as exploration and formation. However, this is highly c
arXiv:2610.11206v1 Announce Type: new Abstract: Flat loss landscapes have long been linked to better generalization in neural networks. However, its role as a causal mechanism for generalization is le
arXiv:2610.12048v1 Announce Type: new Abstract: Deep neural networks, including large language models, have achieved remarkable performance across various tasks. However, they are prone to overconfide
arXiv:2610.11706v1 Announce Type: new Abstract: Self-blended images are widely used to train face-swap detectors, but primarily capture blending artifacts. We investigate whether adding illumination i
arXiv:2610.11776v1 Announce Type: new Abstract: Long-term personalization requires language models to use interaction history to track users' preferences across sessions. Parametric memory encodes thi
arXiv:2610.11115v1 Announce Type: new Abstract: The escalating size of pretrained neural networks has rendered model compression a prerequisite for deployment under stringent memory and compute constr
arXiv:2610.11284v1 Announce Type: cross Abstract: Diffusion-based LLMs (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs by enabling bidirectional parallel refinemen
arXiv:2610.11790v1 Announce Type: new Abstract: Byte-level language models such as the Byte Latent Transformer (BLT) group bytes into patches and run their large global model once per patch. BLT start
arXiv:2610.11303v1 Announce Type: new Abstract: Radiology report generation can automatically generate clinical descriptions from X-ray images, thereby significantly improving the efficiency of radiol
arXiv:2609.34181v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they still suffer from overthinking, generating redundant reasoning
arXiv:2610.11347v1 Announce Type: new Abstract: Physically grounded manipulation of articulated objects requires understanding both the maximum forces encountered during contact and the work performed
arXiv:2312.01221v2 Announce Type: replace Abstract: Quantum Natural Language Processing (QNLP) is taking huge leaps in solving the shortcomings of classical Natural Language Processing (NLP) technique
arXiv:2610.11690v1 Announce Type: cross Abstract: In the graph model for conflict resolution (GMCR), a decision maker (DM) either moves the conflict to another state or does nothing. The basic definit
arXiv:2610.11380v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in generative modeling, with their sampling procedures routinely modified to control generation and im
arXiv:2610.10666v1 Announce Type: new Abstract: Understanding why deep neural networks make a given prediction is of great importance for their safe deployment. In computer vision, saliency maps, whic
arXiv:2601.12654v3 Announce Type: replace-cross Abstract: SHAP explanations are widely used in high-stakes settings to justify decisions, yet they can differ substantially across repeated runs, even w
arXiv:2610.11379v1 Announce Type: new Abstract: JEV models make multimodal decisions by directly scoring candidates. Although the common context is encoded once, candidate evaluation can still repeat
arXiv:2610.11459v1 Announce Type: cross Abstract: Outside the linear-Gaussian regime, conditional sampling from Gaussian processes (GPs) is challenging. Recent methods such as FlowGP (Moss et al., (20
arXiv:2610.12102v1 Announce Type: cross Abstract: Flow matching has emerged as a scalable paradigm for training high-quality generative models, but sampling from the learned probability flow requires
arXiv:2610.12245v1 Announce Type: new Abstract: Social and service robots in public spaces need to anticipate which nearby person is about to approach and touch them, so that a response can be prepare
arXiv:2510.04440v2 Announce Type: replace Abstract: We develop a source-driven fractional heat-kernel framework for semi-super-vised graph learning that combines nonlocal propagation with sustained la
arXiv:2610.11412v1 Announce Type: new Abstract: We propose Fresco++, a unified optimization framework for fine-grained and view-consistent head avatar reconstruction. Head avatar optimization is typic
arXiv:2602.01683v2 Announce Type: replace-cross Abstract: Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous percep
arXiv:2610.11472v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning often improves language-model performance by giving models additional computation before answering. However, explicit C
arXiv:2610.12241v1 Announce Type: new Abstract: Microscopic robots require accurate task geometry despite changes in language, parts, and focus. We present a semantic-to-physical framework that maps i
arXiv:2610.10642v1 Announce Type: cross Abstract: This paper studies the construction of an explanatory space for a weighted naive Bayes classifier from the supervised representation induced by the mo
arXiv:2610.11818v1 Announce Type: cross Abstract: While massive, closed-source Vision-Language Models (VLMs) set strong benchmarks for document understanding, their dependence on commercial APIs limit
arXiv:2610.11787v1 Announce Type: new Abstract: Multimodal depression assessment offers a promising approach to analyzing behavioral patterns associated with depression. However, existing methods ofte
arXiv:2610.11770v1 Announce Type: new Abstract: AI-Native video creation is shifting from isolated video clips toward iterative video creation workflows. However, existing datasets remain largely vide
arXiv:2610.12305v1 Announce Type: new Abstract: As Multimodal Large Language Models (MLLMs) can describe increasingly complex visual scenes, token-level grounding becomes crucial. Yet, when an MLLM ge
arXiv:2610.12009v1 Announce Type: cross Abstract: Physics-informed machine learning has gained significant attention in recent years. In regimes of limited data, parametrized Gaussian processes have b
arXiv:2512.21476v2 Announce Type: replace-cross Abstract: Colonoscopic Polyp Re-Identification (ReID) aims to match the same polyp across a large gallery of images captured from different viewpoints a
arXiv:2409.01656v4 Announce Type: replace-cross Abstract: We consider the problem of estimating graph limits, known as graphons, from observations of sequences of sparse finite graphs. In this paper w
arXiv:2607.08987v2 Announce Type: replace Abstract: Spectral embedding methods are widely used for dimensionality reduction and clustering of high-dimensional datasets with intrinsic low-dimensional s
arXiv:2610.11231v1 Announce Type: new Abstract: Small vision-language models may be able to read external evidence yet struggle to obtain it. We introduce Harness Compilation (HC), an offline procedur
arXiv:2610.12147v1 Announce Type: new Abstract: False negatives remain a critical limitation of computer-aided diagnosis (CAD) systems for breast cancer screening due to delayed detection and treatmen
arXiv:2610.11877v1 Announce Type: new Abstract: Automated research systems support literature synthesis, ideation, experiments, writing, and peer review, but their evaluation is dispersed across tasks
arXiv:2610.10640v1 Announce Type: cross Abstract: Diffusion samplers can reduce computation by generating selected spectral coordinates and filling the remaining directions with noise. How many direct
arXiv:2610.10795v1 Announce Type: new Abstract: We study ranking models by population-average utility from pairwise comparisons when preferences vary across users and tasks. Prior work shows that a si
arXiv:2610.12250v1 Announce Type: cross Abstract: Pretrained audio encoders are reused for downstream tasks that are often unknown when the encoder is trained, so their usefulness depends partly on wh
arXiv:2610.05671v2 Announce Type: replace Abstract: Automatic prompt optimization (APO) has been widely employed to adapt large language models without updating their weights, yielding promising resul
arXiv:2610.12455v1 Announce Type: cross Abstract: On a film set, the camera move is committed during a take. Generative video reshooting lets filmmakers change it afterward, but may require hallucinat
arXiv:2610.12064v1 Announce Type: new Abstract: Digital technologies have made Islamic narratives more accessible, but existing platforms provide limited support for structured learning and comprehens
arXiv:2610.11144v1 Announce Type: cross Abstract: Single-image nutrition estimation can fail silently when visible foods are missed. Even when a food is correctly identified, its proposed region may n
arXiv:2610.11783v1 Announce Type: new Abstract: Shared e-scooter services have become a widely adopted urban transport mode. While most users ride responsibly, alcohol intoxication stands out among th
arXiv:2610.11566v1 Announce Type: new Abstract: Existing Open-Ended Deep Research (OEDR) systems primarily generate reports from scratch, making them inefficient for scenarios where research reports n
arXiv:2610.12142v1 Announce Type: new Abstract: Electromagnetic spectrum monitoring increasingly requires flexible analysis beyond task-specific recognition and detection. Multimodal large language mo
arXiv:2610.11025v1 Announce Type: cross Abstract: Exploratory data analysis (EDA) is rarely open-ended in practice: analysts work from high-level domain questions toward the concrete analyses that can
Interesting paper from Sakana AI on memory for recurrent models. Recurrent models are good at state tracking, but they usually keep everything in one hidden vector, so short-term computation and long-
arXiv:2610.10548v1 Announce Type: cross Abstract: Spaced repetition software schedules reviews with a memory model fit to review logs. Accuracy on a test set is not sufficient evidence of quality sinc