arXiv Machine Learning June 11, 2026 By Andrei Panferov, Davit Melikidze, Martin Jaggi, Dan Alistarh

Apertus LLM Family Expansion via Distillation and Quantization

Read the original on arXiv Machine Learning →

arXiv:2605. 29128v2 Announce Type: replace Abstract: The wide adoption of LLMs has led to their use in great variety of applications and scenarios, such as chatbot assistants and data annotation, creating the need for the models to satisfy certain budget and hardware constraints.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 1

Large Databases Need Small, Open-Weight Language Models

arXiv:2606. 31808v1 Announce Type: new Abstract: Language model systems built around proprietary APIs often operate on a token-based cost model.

By Parker Glenn, Alfy Samuel

llms efficiency

arXiv AI

Jun 16

LLM4RTL: Tool-Assisted LLM for RTL Generation

arXiv:2606. 15500v1 Announce Type: cross Abstract: Large language models (LLMs) have facilitated impressive progress in software engineering, code generation, tooling, and systems.

By Jing Jin, Robert Chu, Ning Yan, Masood S. Mortazavi

llms fine-tuning benchmarks

arXiv AI

Jun 26

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

arXiv:2606. 26650v1 Announce Type: cross Abstract: In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs.

By Shigeng Wang, Chao Li, Yangyuxuan Kang, Jiawei Fan, Anbang Yao

llms efficiency benchmarks

arXiv AI

Aug 5

TQLite: Multi-LLM Jury Guided Distillation for Real-time MQM Translation Quality Evaluation

arXiv:2608. 02975v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive performance in MQM-based translation quality (TQ) evaluation, and recent advances in large reasoning models (LRMs) promise even greater improvements.

By Bhavin Jawade, Cameron R. Wolfe

llms efficiency benchmarks

Hugging Face Trending Papers

Jun 25

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes.

llms efficiency benchmarks

arXiv Machine Learning

Jul 8

FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models

arXiv:2607. 05711v1 Announce Type: new Abstract: Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications.

By Bowen Xue, Zihan Min, Xingyang Li, Zhekai Zhang, Haocheng Xi, Lvmin Zhang, Maneesh Agrawala, Jun-Yan Zhu, Song Han, Yujun Lin, Muyang Li

diffusion reinforcement-learning fine-tuning efficiency

Related stories

Large Databases Need Small, Open-Weight Language Models

LLM4RTL: Tool-Assisted LLM for RTL Generation

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

TQLite: Multi-LLM Jury Guided Distillation for Real-time MQM Translation Quality Evaluation

CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

FourTune: Towards Fully 4-Bit Efficient Post-Training for Diffusion Models