Paper

Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering

Unreadunread

AI summary

arXiv:2606. 11386v1 Announce Type: new Abstract: Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplored.

Reading status

Priority

About this paper

Authors: Cheng-Kuang Chang, Kai-Wei Chang, Alexander H. Liu, James Glass
Released: 2026-06-11 (28d ago)
Topic: Related to current project
Relation to my work: Read next because Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, text, persona, word, rect, under, correct, eval. Source: arxiv cs.CL (NLP).
arXiv: 2606.11386

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.