The results show that RegionFM maintains performance comparable to less interpretable fine-tuning approaches while providing anatomically grounded explanations, and better aligns model explanations with anatomy-based clinical reasoning while maintaining competitive predictive performance.
A central lesson is to validate uncertainty in the region, and against the error target, for which it will be used, to validate uncertainty in the region, and against the error target, for which it will be used.
Experimental results show that action filtering provides negligible safety improvement, while observation filtering reduces near mid-air collisions by 90% and remains robust to the barrier function's tradeoff between separation distance and closing rate, and suggest that preserving the policy's decision authority outperforms overriding its actions with hand-designed constraints.
Language models prompted with cultural personas increasingly stand in for human respondents in cross-cultural research. Their responses separate personas cleanly, and that separation is read as evidence of a cultural point of view. We show that the separation is real, that the point of view is not, and that one criterion tells them apart. A trait is structure internal to one respondent that survives a change of measurement frame; a bias needs only group-specific item means. To test for the first, we represent a single response set as an Item--Dimension matrix and treat its correlation matrix as a point on the manifold of symmetric positive definite matrices. In humans this carries what a trait should: it reproduces across test--retest sessions sharing no items, order or context ($r=0.77$, $N=89$); on public NEO-PI-R data it identifies individuals at up to $76\%$ against a $0.4\%$ chance level ($N=263$); and it predicts GPA ($R^2=0.281$, $p=0.003$) where BigFive aggregates from the same responses predict nothing ($R^2=0.018$). In four frontier LLMs it returns nothing. Persona structure is readable only while every instance shares one item order: give each its own order and separation falls from $94.7\%$ to chance, while realigning instances to \emph{any} shared random order restores it to $82$--$84\%$. Responses generated independently item by item, with no latent structure, reproduce the entire pattern. The cultural signal is a group template, not a property of any instance, and alignment regimes differ only in which stereotype survives on the surface.
Yu Yuan· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Self-Organized Conformal Prediction (SOCP), a calibration scheme that discovers input-space groups with an unsupervised Self-Organizing Map (SOM) trained without calibration labels, is introduced, providing a concise route to group-local calibration without supervised partitions or predictor retraining with a diagnostic toolkit.
Louis Berthier, A. Shokry, M. Moreaud et al.· arXiv.org· 0 citations
Experiments show that J-LAW's factor-graph representation can improve long-horizon latent consistency and recover more reliable predictive states under partial observations, forming a foundation for future integrated localization and planning systems.
This paper proposes MultiHashFormer, a new framework that allows hash-based autoregression that consistently outperforms standard Transformer LMs across multiple benchmarks and shows that the model handles multilingual vocabulary expansion with a constant parameter footprint without any modifications.
FracEvent, an event simulator that models this pixel-level lifecycle with fractional-relaxation voltage dynamics, improves the temporal structure of generated events and achieves stronger downstream-transfer results than competing simulator baselines, showing its practical value for event-camera simulation.
It is argued that, even when an LLM has been well aligned in (post-)training, it may still fail to maximise the aligned value in reasoning, and the utility discrepancy between a model's deployed reasoning strategy and its rational counterpart whose responses maximise utility in the steepest direction is formalised.
Comprehensive empirical evaluations demonstrate PEAR significantly improves average accuracy over the strongest debate baselines, and theoretically characterize PEAR as an equivariant sparse router: it preserves accuracy under agent relabeling while reducing routing complexity and improving generalization.
Yang Feng, Ziwei Xu, Xia Hu et al.· arXiv.org· 0 citations
How AI itself might continue to develop in a post-AGI world along the continuum of machine intelligence is investigated, which can intuitively be understood as a system that is more intelligent and cognitively capable than large organisations of humans.
Tim Genewein, Matija Franklin, Alexander Lerchner et al.· arXiv.org· 4 citations
The results show that compact fine-tuned models can preserve most extraction accuracy, but model selection must account for prompt choice, throughput, and serving-stack behavior.
Donghao Huang, Tomas Drietomsky, Benjamin Barrett et al.· arXiv.org· 1 citation
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
Adaptive AI agents can help make BIM data more machine-readable by navigating IFC models, interpreting inconsistent information, and mapping it to defined standards. In this blog, Alok Rawat shares findings from a real-world pilot in construction workflows. The post Adaptive AI Agents in Construction Workflows appeared first on GPT-Lab.
