Prépublication
· 2026 arXiv
EN
A reasoning trace can accompany a correct answer without providing effective supervision for a particular student. We study how to construct traces that improve learning beyond answer-only supervision by considering both their intermediate content and their ac...
Shaoang Li, Yanhang Shi et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
Self-driving laboratories (SDLs) accelerate scientific discovery by automating experimental execution and optimization. AI agents can increasingly propose new experiments, but existing SDLs can only run the procedures they were built for. Adapting them to a ne...
Jiaru Bai, Yuchi Zhao et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Speculative decoding typically characterizes speedup by draft tokens accepted per verification round. Lossless verification preserves the target model's output distribution and thus expected completion length, making this metric a meaningful efficiency proxy....
Chiatzen Wang, Bill Xu et al.
#cs.CL
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