Emergent generative AI technologies, while remarkably beneficial across several tasks and domains, can suffer from unforeseen vulnerabilities and difficult-to-anticipate failure modes. Such failure modes can disparately affect vulnerable communities. This paper investigates two well-known vision language models (VLMs)...
Soumyajit Datta, Arka Dutta, Ashiqur R. KhudaBukhsh· 0 citations
Despite the proliferation of sovereign Environmental, Social, and Governance (ESG) metrics, traditional linear macro-financial models systematically misprice Foreign Direct Investment (FDI) tail risks during systemic shocks. This paper demonstrates that sovereign risk transmission is fundamentally non-linear. Using a f...
Motivation: Interactive web tools enabling non-programmers to explore single-cell datasets, embeddings, gene expression, metadata, and marker genes are standard laboratory infrastructure. However, actively maintained tools (e.g., ShinyCell, ScRDAVis, sCIRCLE) rely on R Shiny and require Seurat objects. Python/scanpy, t...
Hao Xuan, Yu Huang, Jiang Bian et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The microphysics of dark matter (DM) is imprinted on cosmological structure across an enormous dynamic range. Nonlinear cosmological observables are most reliably modeled with N-body and hydrodynamic simulations. However, systematic N-body scans over DM theory space are prohibitively expensive. Machine learning emulato...
Ibrahim Elsharkawy, David Curtin, Yonatan Kahn et al.· 0 citations
KPPax, a kinetic preprocessor that generates differentiable, just-in-time compiled, and vectorisable chemistry code in JAX from mechanisms written in the KPP language, makes KPP mechanisms directly usable for parameter estimation and hybrid physics--machine-learning modelling.
Language models pretrained on web corpora collected over multiple years learn both general and domain-specific knowledge. How these different kinds of knowledge are learned as pretraining progresses remains unclear. Recent point-in-time models trained on web snapshots from different years provide a way to probe how kno...
Chang Su, Bin Wu, Emine Yilmaz et al.· 0 citations
When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the decision criteria. On hidden-profile tasks both look attractive, because how widely a fact is held is confounded with whet...
Anouar Imel, Imad Charradi, Abderrahman Sghir et al.· 0 citations
We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and Timestral-123M take the top two places on every metric. We achieve this with th...
Adrien Petralia, A. Gavaudan, Artjom Joosen et al.· 1 citation
Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems constructed from real-wo...
Chanwoo Park, Jaywoong Jeong, Zachary Wojtowicz et al.· 0 citations
GUI memory should preserve the results of past actions and learn reusable operations. This is difficult in long-horizon workflows, where agents must use information across applications and useful operations are interleaved with failed attempts. We introduce Task Advancement Memory (TAM), which defines task advancement...
Agents built on large language models are increasingly allowed to take consequential actions: cancelling bookings, issuing refunds, changing accounts. The rules that govern those actions, such as "obtain the customer's explicit confirmation before changing anything", are usually stated in the prompt and followed only a...
