arXiv Machine Learning June 4, 2026 By Hanna Mazzawi, Benoit Dherin, Michael Munn, Adrian Goldwaser, Michael Wunder, Javier Gonzalvo

Transmuting prompts into weights

Read the original on arXiv Machine Learning →

arXiv:2510. 08734v3 Announce Type: replace Abstract: A growing body of research has demonstrated that the behavior of large language models can be effectively controlled at inference time by directly modifying their internal states, either through vector additions to their activations or through updates to their weight matrices.

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

llms

arXiv Machine Learning

Jul 10

Prompt Compression via Activation Aggregation

arXiv:2607. 08399v1 Announce Type: cross Abstract: Large language models process prompts by propagating activations through dozens of layers before generating a response.

By Thibaud Ardoin, Semira Einsele, Evis Bregu, Gerhard Wunder

llms

arXiv AI

Aug 5

The Transformer Revolution, Part 1: Dynamic Processing through Output- Weight Interconnections

arXiv:2608. 03921v1 Announce Type: new Abstract: This paper offers a new interpretation of the Transformer during inference.

By Marco Giunti, Fabrizia Giulia Garavaglia

llms safety

arXiv AI

Jul 2

CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization

arXiv:2511. 05747v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning enhances the problem-solving ability of large language models (LLMs) but leads to substantial inference overhead, limiting deployment in resource-constrained settings.

By Ziqian Bi, Yinzhi Wang, Tianyang Wang, Junfeng Hao, Benji Peng, Xinyuan Song

llms computer-vision nlp

arXiv AI

Aug 11

The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections

arXiv:2608. 03921v2 Announce Type: replace Abstract: This paper offers a new interpretation of the Transformer during inference.

By Marco Giunti, Fabrizia Giulia Garavaglia

llms safety

arXiv AI

Jun 16

Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate

arXiv:2606. 16360v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting improves reasoning in large language models (LLMs) by externalizing intermediate computation as discrete text tokens, but this textual interface also introduces redundancy and inference overhead.

By Hanyu Lin, Min Cai, Jiawei Wen, Haodi Zhang

llms

arXiv AI

Jul 22

Fluid Reasoning Representations

arXiv:2602. 04843v2 Announce Type: replace Abstract: Frontier large language models increasingly solve complex tasks involving abstract concepts through extended test-time thinking.

By Dmitrii Kharlapenko, Terry Jingchen Zhang, Arth Singh, Alessandro Stolfo, Arthur Conmy, Mrinmaya Sachan, Zhijing Jin

llms

Related stories

Prompt Compression via Activation Aggregation

The Transformer Revolution, Part 1: Dynamic Processing through Output- Weight Interconnections

CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization

The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections

Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate

Fluid Reasoning Representations