技术雷达TECH RADAR · GITHUB · ARXIV · HACKER NEWS

Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be rendered, but first-c

Junxiang Xu, Ruisi Wang, Fanyi Pu

In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed MLLMs to continually evolve from streaming unlabeled data. Existing unsupervised p

Kaichen Li, Zhilin Zhu, Jianhao Huang

Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such as RGB and pose, overlooking physiological dynamics such as muscle mechanics and often modeling actio

Hao Yin, Paritosh Parmar, Lijun Gu

Designing machine learning algorithms for wireless resource management is labour-intensive: the architecture, the loss function and the training recipe are all specified by hand. We demonstrate that t

Ahmad Khan, Akram Bin Sediq, Sara Azadegi Naeini

We present a first application of sparse-autoencoder-based mechanistic interpretability to particle physics. Studying a neutrino foundation model pretrained on IceCube data and fine-tuned for directio

Raphaël Bonnet-Guerrini, Johann Ioannou-Nikolaides, Inar Timiryasov

Addressing critical global challenges, from food security and disaster risk to disease outbreaks and socio-economic vulnerability, demands high-fidelity geospatial modeling. However, building predicti

Evelyn Ma, Rama Kumar Pasumarthi, Kishwar Shafin

Large language models write correct code for isolated problems but remain far weaker at autonomous machine-learning development, where an agent must revise data pipelines, models, and validation over

Jiarui Yan, Weiwei Sun, Sijie Li

Deep neural networks often exploit spurious associations in their training data, a failure known as shortcut learning. Concept-based explainability methods screen for shortcuts by testing whether conc

Roshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer

Collective intelligence can emerge when individuals coordinate through a shared environment, allowing local actions to accumulate into durable social organization. Language-model agents offer a new su

Subhadeep Pal, Fiona Y. Wang, Markus J. Buehler

Intent misinterpretation during vehicle interactions causes recurring planning failures. We study a decision layer in which a language-guided intent module reads structured descriptors, computes a smo

Cong Xu, Ravi Sankar

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论

原文 · 讨论