AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

AudioChat: Unified Audio Storytelling, Editing, and Understanding with Transfusion Forcing

William Chen, Prem Seetharaman, Rithesh Kumar, Oriol Nieto, Shinji Watanabe, Justin Salamon, Zeyu Jin

ICML 2026 · Large language models › Language, safety and interpretability · approach: Speech and audio language models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add diffusion forcing noise and MLLM representations (Transfusion Forcing) versus plain DiT conditioned on clean input audio (ablation)audio editing model · StoryGen-Eval editingeditFLAM: 2.7 -> 18.6Improved
add structured chain-of-thought reasoning to the diffusion LLM (ablation)AudioChat · StoryGen-Eval editingdelta multiFLAM: 27.8 -> 11.7Improved
give the storytelling stage access to the input audio (end-to-end) instead of cascading from LLM text (ablation)AudioChat · StoryGen-Eval editingdelta multiFLAM: 26.7 -> 11.7Improved
use SCT instead of MoT architecture (ablation)AudioChat · StoryGen-Eval editingeditFLAM: 9.6 -> 18.6Improved
use SCT instead of vanilla dense model (ablation)AudioChat · StoryGen-Eval editingdelta multiFLAM: 15.5 -> 11.7Improved
use SCT instead of dense or MoT for text-to-audio (ablation)AudioChat · AuditionSFX T2ACLAPscore: 65.3 (Dense), 65.8 (MoT), 65.5 (SCT)No clear effect
AudioChat vs WavJourney for storytellingaudio storytelling · StoryGen-Eval storytellinglatency (s): 628 -> 32Improved
decompose abstract prompt with an LLM before SAOStable Audio Open · StoryGen-Eval storytellingmultiFLAM: 35.6 -> 32.2Hurt
use previous generation instead of ground truth as input in two-turn editingAudioChat · StoryGen-Eval two-turn editingdelta multiFLAM: 10.5 -> 11.8No clear effect
evaluate on real AudioCaps audio instead of syntheticAudioChat · editFLAMeditFLAM: 18.6 -> 15.5Hurt
replace OpenFLAM with PE-A embedding model in metrics (ablation)evaluation metrics · StoryGen-Eval editingmethod rankingNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy