arXiv:2606.24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely…
arXiv:2606.19910v2 Announce Type: replace Abstract: Training automated pronunciation assessment often relies on labeled learner errors or non-native corpora that are costly to collect. We propose a…
arXiv:2506.14293v4 Announce Type: replace-cross Abstract: We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song. To the best of our knowledge, there are no…
arXiv:2606.19623v2 Announce Type: replace Abstract: Graph neural networks (GNNs) offer a flexible framework for learning from scientific data with physical, biological, or functional associations. One promising…
arXiv:2606.23825v1 Announce Type: new Abstract: Efficient small object detection is bottlenecked by the inherent feature scarcity of tiny targets, which is further aggravated by operations of…
arXiv:2606.23874v1 Announce Type: cross Abstract: Understanding how the architecture of neural networks shapes the computations they carry is a central challenge in neuroscience and machine learning.…
arXiv:2606.24418v1 Announce Type: cross Abstract: Data augmentation is a simple and model-agnostic approach for exploiting known invariances in learning problems. Given a group acting on the…
arXiv:2606.24047v1 Announce Type: new Abstract: One of the significant mental health issues affecting female sex workers (FSWs) is mental disorders, especially depression. Exposure to violence, stigma,…
arXiv:2606.24129v1 Announce Type: new Abstract: For a wheelchair user, a standard blue line on a map is often a broken promise. While platforms like OpenStreetMap (OSM)…
arXiv:2606.23937v1 Announce Type: new Abstract: Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision…
arXiv:2602.22810v2 Announce Type: replace Abstract: In this work, we present the first theoretical analysis of multi-agent imitation learning (MAIL) in linear Markov games where both the…
arXiv:2606.23858v1 Announce Type: new Abstract: A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network…
arXiv:2606.23763v1 Announce Type: new Abstract: Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens. However, we observe that highest attention regions are not…
arXiv:2511.08065v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) promise highly energy-efficient computing, but their adoption is hindered by a critical scarcity of event-stream data. This…
arXiv:2606.24715v1 Announce Type: new Abstract: We consider the problem of model selection between probabilistic models on data sets of time series. Chosen a proper scoring rule,…
arXiv:2606.19791v2 Announce Type: replace-cross Abstract: The challenge associated with recognizing dysarthric speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has…
arXiv:2506.08026v4 Announce Type: replace Abstract: Real-time market prediction services need correct predictions before a decision deadline; a correct prediction delivered late is not usable. TIP-Search studies…
arXiv:2510.00866v3 Announce Type: replace-cross Abstract: Large-scale models are pretrained on massive web-crawled datasets containing documents of mixed quality, making data filtering essential. A popular method is…
arXiv:2606.09313v2 Announce Type: replace Abstract: Retrieval algorithms are used to estimate atmospheric concentrations of greenhouse gases (GHGs), such as carbon dioxide (CO2) and methane (CH4), by…
arXiv:2503.13505v3 Announce Type: replace-cross Abstract: Generative Pretrained Transformers (GPTs) are foundational Large Language Models (LLMs) for text generation. However, individual LLMs often produce inconsistent outputs and…
arXiv:2606.24628v1 Announce Type: cross Abstract: Deploying robots in unstructured real-world environments needs accurate, interactive models of the objects. Constructing these models at scale remains a critical…
arXiv:2606.24588v1 Announce Type: new Abstract: Noise in neural computation is typically regarded as a disturbance, but its spatial distribution may also actively regulate which parts of…
arXiv:2606.24427v1 Announce Type: cross Abstract: Nonlinear mixed-effects models are widely used to analyze longitudinal data, but existing open-source software often supports only a limited subset of…
arXiv:2606.24026v1 Announce Type: new Abstract: Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult to…