arXiv Machine Learning August 7, 2026 By Ayushi Agarwal

Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study

Read the original on arXiv Machine Learning →

arXiv:2608. 05164v1 Announce Type: cross Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested.

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

arXiv Machine Learning

1d ago

Architecture-Dependent Causal Transfer of Activation States Across Large Language Models

arXiv:2608. 16347v1 Announce Type: cross Abstract: Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and latency.

By Fernando Cardenas Piepereit

llms safety

arXiv AI

Aug 11

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models

arXiv:2608. 08829v1 Announce Type: cross Abstract: Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the injection layers globally per task.

By Muhammad Faishal Adly Nelwan, Alfan Farizki Wicaksono

llms rag safety

arXiv AI

Jul 13

CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding

arXiv:2607. 08974v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) inherit semantic capabilities from pretrained VLMs, yet large-scale post-training on robot data and architectural modifications can reshape the backbone so extensively that it becomes difficult to isolate what the VLM contributes to control.

By Yuri Ishitoya, Jeremy Siburian, Masashi Hamaya, Kuniaki Saito, Cristian C. Beltran-Hernandez, Mai Nishimura

robotics fine-tuning multimodal

arXiv AI

Jul 21

Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective

arXiv:2607. 18026v1 Announce Type: new Abstract: Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment?

By Jiahe Fan, Yinghao Hou, Si Chen, Aiyuan Zhang, Hong Xie, Defu Lian

llms efficiency benchmarks safety

arXiv AI

Jun 18

From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging

arXiv:2506. 14126v2 Announce Type: replace-cross Abstract: Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets.

By Stefan Horoi, Guy Wolf, Eugene Belilovsky, Gintare Karolina Dziugaite

fine-tuning

arXiv AI

Jun 9

Phantom transitions in language model fine-tuning

arXiv:2606. 07559v1 Announce Type: cross Abstract: Fine-tuning a language model on contexts whose correct completion has a near-synonym competitor often fails silently.

By Vaibhav Prakash, Jayasri Dontabhaktuni

llms rag fine-tuning

Related stories

Architecture-Dependent Causal Transfer of Activation States Across Large Language Models

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models

CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding

Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective

From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging

Phantom transitions in language model fine-tuning