arXiv Computation and Language September 17, 2026 By Marco Simoni, Aleksandar Fontana, Giulio Rossolini, Andrea Saracino

DANTINOX: A Unified Framework for Multi-Paradigm Language Modeling

Read the original on arXiv Computation and Language →

The paper introduces DantinoX, an open‑source JAX/Flax library that unifies autoregressive decoding, discrete masked diffusion, and continuous flow‑matching language modeling under a single modular Transformer backbone. By keeping the backbone, tokenizer, initialization, and training infrastructure consistent, users can switch between generation paradigms, attention mechanisms, or hardware topologies with only a configuration change. This design enables controlled cross‑paradigm comparisons within one API for training, streaming inference, and benchmarking.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Machine Learning

Jun 5

A Survey on Diffusion Language Models

arXiv:2508. 10875v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm.

By Tianyi Li, Mingda Chen, Bowei Guo, Zhiqiang Shen

llms diffusion nlp efficiency multimodal benchmarks

arXiv AI

Jun 18

Towards Understanding What State Space Models Learn About Code

arXiv:2602. 06774v2 Announce Type: replace Abstract: State Space Models (SSMs) have emerged as an efficient alternative to the Transformer architecture.

By Jiali Wu, Abhinav Anand, Shweta Verma, Mira Mezini

llms fine-tuning

arXiv Computation and Language

Sep 1

Simulstream: Open-Source Toolkit for Evaluation and Demonstration of Streaming Speech-to-Text Translation Systems

Simulstream is an open‑source toolkit designed to evaluate and demonstrate streaming speech‑to‑text translation systems. It supports both incremental and re‑translation decoding on long‑form speech, offers fine‑grained logging for quality and latency metrics, and includes an interactive web interface for real‑time visualization and comparison. The toolkit addresses the fragmented evaluation landscape by providing a unified framework that accommodates different decoding strategies and input formats.

By Marco Gaido, Sara Papi, Mauro Cettolo, Matteo Negri, Luisa Bentivogli

benchmarks

arXiv Computation and Language

Aug 31

CoFrGeNet: Continued Fraction Architectures for Language Generation

CoFrGeNet introduces Continued Fraction Generative Networks, a new function class that replaces Multi-head Attention and Feed-Forward Networks in Transformer blocks with fewer parameters. The architecture includes custom gradient formulations for efficient optimization and can be plugged into existing Transformer workflows with minimal changes. Experiments on GPT2‑xl and Llama3 show competitive or superior performance on downstream tasks while using 1/2 to 2/3 of the original parameters and shorter pre‑training time.

By Amit Dhurandhar, Vijil Chenthamarakshan, Dennis Wei, Tejaswini Pedapati, Karthikeyan Natesan Ramamurthy, Rahul Nair

llms

arXiv AI

Jul 14

Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting

arXiv:2607. 10661v1 Announce Type: cross Abstract: Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks.

By Zipeng Gao, Zhi Zheng, Qingrong Xia, Junda Lin, Ziwei Zhao, Tong Xu, Zhefeng Wang, Enhong Chen

llms efficiency benchmarks

arXiv Machine Learning

Jul 21

OpenLanguageModel: Readable and Composable Small-Language-Model Pretraining for Education and Research

arXiv:2607. 16669v1 Announce Type: cross Abstract: OpenLanguageModel (OLM) is an open-source PyTorch library for building and pretraining small language models while keeping their machinery visible.

By Tavish Mankash, Vardhaman Kalloli, Keshava Prasad, Deepan Muthirayan

llms benchmarks