Causal discovery with latent confounding is particularly challenging, but a common setting in real-world data. In this work, we focus on linear causal models with latent confounding, represented by acyclic directed mixed graphs (ADMGs). Existing methods that fully identify ADMGs typically assume non-Gaussianity or grap...
Danru Xu, Aapo Hyv\"arinen, Sara Magliacane· 0 citations
Cascade world-action models (WAMs) use predicted visual futures to condition robot actions, but inherit costly iterative inference from diffusion-pretrained experts. We ask what a single-step predicted future must preserve to support accurate single-step action prediction. In the evaluated WAM, resampling video noise h...
Shao-Yi Zheng, Zhong-Tao Jiang, Yue Peng et al.· 0 citations
AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that runs the model, do not record who may act on this memory, so an instruction hidden in a fetched page can be treated as the user's own instruction. We propose ClawMMU, a protection layer that labels e...
Jin-Hao Hu, Bardia Mohammadi, Mofasshara Rafique et al.· 0 citations
It is suggested that the evaluated LLMs respond to surface cues rather than to the mechanisms that make a passage manipulative, which would suggest that the evaluated LLMs respond to surface cues rather than to the mechanisms that make a passage manipulative.
Yousra Fettach, T. De Bie· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is argued that continuous-time graph learning should identify low-dimensional states sufficient for future prediction rather than reconstruct the full history, and proposed PreDyG, a lightweight model whose capacity is matched to the intrinsic predictive dimension.
Real-time video generation, interactive world models, and on-device image synthesis are almost a reality. Diffusion Transformers (DiT) achieve excellent sample quality, shifting the bottleneck to the throughput of the models themselves. Natural images are inherently sparse, as large portions of an image are often backg...
Jarek Liesen, Matthew T. Jackson, Benjamin Ellis et al.· 0 citations
PULSE, an event-driven framework for personalized opportunistic learning that treats each encounter as an online collaboration decision, selecting either no interaction or a promising nearby peer, shows that selective opportunistic collaboration can provide effective personalization while limiting communication and res...
M. G. Campana, Dariush Salami, Hüseyin Yiğitler et al.· 0 citations
Multilingual evaluations often score a model's opening yes or no, a token that also carries model and language answering conventions. We ask when different ways of eliciting and reading an answer recover the same judgment, and when they measure an answer habit. We collect 1.1 million replies from eight models in six la...
Groundwater in Ghana's Densu River Basin remains a key domestic water source, but multi-metal contamination threatens children's health. Previous deterministic hazard index assessments provide limited treatment of uncertainty, co-exposure, and spatial variability. This study applies a Bayesian probabilistic framework f...
T. Ansah-Narh, G. Y. Afrifa, J. B. Tandoh et al.· 0 citations
Concept Bottleneck Models (CBMs) promise predictions that humans can inspect and correct through concepts such as"curved beak". Yet on CUB-200-2011, their standard benchmark, progress is measured like that of ordinary classifiers: by task and concept accuracy. Neither reveals whether the label is predicted from the exp...
S. Saralajew, Eleonora Poeta, Eliana Pastor et al.· 0 citations
A causal, training-free linker that allows a frozen streaming diarizer to track more speakers than it has output slots and only relabels, so missed speech and false alarm are identical to the host's and every gain is a reduction in speaker confusion.
A. Menon, Kumarmanas Nethil, Kavya Manohar· 0 citations
A compact explainability-driven framework for comparing encoders trained with classification-only and caption-generation supervision on CUB-200 provides a systematic basis for assessing learned representations and comparing alternative training and transfer-learning strategies.
