CORTEXA
← Browse
arxivcs.LG2026-07-02

Probing Chemical Language Models: Effects of Pre-training and Fine-tuning

Anna Karnysheva, Dietrich Klakow, Ji-Ung Lee

Chemical language models (CLMs) are trained with linearized representations such as SMILES, yet it remains unclear which chemically meaningful substructures they encode. To foster a better understanding of CLMs, we conduct a systematic study and probe for 78 molecular substructures across eight pre-trained and six randomly initialized models. We furthermore study how fine-tuning on chemical downstream tasks affects the learned representations of molecular substructures. Our results show that pre-training generally improves molecular structure awareness of CLMs, particularly in the upper layers. Moreover, randomly initialized models already encode ring structures well in the first layer. Our analysis on two chemical downstream tasks further reveals that, interestingly, fine-tuning affects task-relevant molecular substructures more than others, indicating that the changes in the representations follow chemical theory.

View free PDFSource page

Related papers

arxivcs.LG2026-07-19

Robust Assamese Speech Recognition through Controlled Fine-Tuning of Whisper Models

Ganapati Das, Dwipen Laskar, Hasin Afzal Ahmed, Sanjib Kr Kalita, Kshirod Sarmah, Hem Chandra Das, et al.

Developing Automatic Speech Recognition (ASR) for morphologically rich, low-resource languages such as Assamese is challenging due to insufficient annotated speech data. The pretrained Whisper model performs poorly on Assamese speech recognition tasks. This paper presents a contr…

View free PDFSource page
arxivcs.LG2026-07-16

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models

Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang

We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC). We consider policy optimization…

View free PDFSource page
arxivcs.CLcs.AIcs.LG2026-07-16

In-Place Tokenizer Expansion for Pre-trained LLMs

Jimmy T. H. Smith, Tarek Dakhran, Alberto Cabrera, Simon S. Lee, Paul Pak, Aditya Tadimeti, et al.

A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time. When those priorities shift, languages added later are split into many more tokens per word, which can raise latency, c…

View free PDFSource page
arxivcs.DCcs.LG2026-07-20

AutoEncoder-Compressed Parallel Split Learning for Pre-trained Model Fine-Tuning

Bas Meuwissen, Vasileios Tsouvalas, Nirvana Meratnia

Distributed Fine-Tuning (DFT) of large-scale Foundation Models (FMs) on resource-constrained edge devices is limited by local compute constraints and communication overhead. Parallel Split Learning (PSL) reduces client-side computation by keeping few model layers on each client a…

View free PDFSource page
arxivcs.LGcs.AI2026-07-20

Federated Lightweight Fine-Tuning

Radhakrishna Achanta, Will Reed

Federated fine-tuning is bottlenecked by communication: FedAvg and pseudo-gradient schemes transmit a payload that scales with the model, and gradient compression shrinks it by only a constant factor. We take a different lever. Mapping networks generate a network's weights from a…

View free PDFSource page
arxivphysics.chem-phcond-mat.mtrl-scics.LG2026-07-16

Full-data accuracy with fewer labels for training and fine-tuning machine-learning force fields

Sheng Bi, Yi-Ze Wang, Jun Cheng

Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows. Active learning can reduce this cost, but standard…

View free PDFSource page