Prépublication
· 2026 arXiv
EN
While deriving text embeddings directly from frozen LLMs has emerged as a promising direction, existing methods focus almost exclusively on English, leaving multilingual settings largely unexplored. In this work, we present the first systematic study of multil...
Ailiang Lin, Zhuoyun Li et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
Sparse autoencoders (SAEs) explain foundation model representations by decomposing activations into sparse combinations of learned dictionary atoms. However, the learned dictionaries can vary across training runs, limiting the reliability and reproducibility o...
Jinho Choi, Hyesu Lim et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Transformer prefill reuses weights across tokens and is dominated by matrix multiplication and activation data movement; single-token decode has limited reuse and is dominated by weight and KV-cache reads. We present FUTRANSFORMER, a CUDA implementation of a L...
Wei Wang
#cs.AI
Prépublication
· 2026 arXiv
EN
Computational drug discovery requires agents to compose scientific operations and adapt to changing evidence and constraints. Here we introduce DrugHarness, an evolvable agent harness coupling composable scientific execution with conditional skill induction. I...
Yuxing Chen, Zhisheng Zhang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Speculative decoding has become a mainstream technique for accelerating large language model (LLM) inference by using a lightweight draft model to generate candidate tokens that are subsequently verified by the target model. However, agentic workloads introduc...
Jiaming Xu, Hanzhen Wang et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
Recent large audio language models (LALMs) have extended their capabilities beyond lexical speech understanding to tasks requiring paralinguistic and non-linguistic audio understanding, such as emotion recognition. However, these models still struggle to relia...
Koki Ryu, Hitomi Yanaka
#cs.SD
Prépublication
· 2026 arXiv
EN
The Italian legislative process is documented in detailed parliamentary records hosted in institutional websites. However, much of this information is available only as unstructured text, limiting its systematic reuse. We applied a controlled, systematic LLM-b...
Matilde Contestabile, Chiara Ferrara et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
Perceived gender inference from names is important for inclusive scientometrics research, yet existing methods perform poorly on non-Western scholars. We address this gap for Chinese names, which appear in two forms, Hanzi and Pinyin, its Romanized form (e.g.,...
Lisette Espín-Noboa, Mingrong She et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
Rings are ubiquitous among the giant planets in the Solar System, yet their presence around exoplanets remains observationally unconstrained. As direct imaging missions such as the Nancy Grace Roman Space Telescope approach first light, understanding the influ...
Samantha N. Hasler, Alexandra Z. Greenbaum et al.
#astro-ph.EP
Prépublication
· 2026 arXiv
EN
The Nancy Grace Roman Space Telescope's Coronagraph Instrument (CGI) will provide the first opportunity to directly detect mature giant exoplanets in reflected light. However, most known radial-velocity planets lie near CGI's sensitivity limit. In contrast, Sa...
Elizabeth Lane, Mary Anne Limbach et al.
#astro-ph.EP
Prépublication
· 2026 arXiv
EN
Galaxy-galaxy lensing (GGL) is a critical probe of cosmology and galaxy formation. However, predicted GGL amplitudes tend to be $\sim 20-40\%$ higher than observations, primarily on small scales, a tension called the lensing-is-low problem. If not resolved thr...
Kimiko Queen, Abigail V. Fisher et al.
#astro-ph.CO
Prépublication
· 2026 arXiv
EN
The evidence, $\mathcal{Z} = p(x | \mathcal{M})$, of a data-generating model $\mathcal{M}$ is a powerful tool in Bayesian frameworks: it enables model inference, model misspecification tests, and goodness-of-fit assessment as an alternative to standard discrep...
Kai Lehman, Jameson Dong et al.
#stat.ML