AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

End-to-end Listen, Look, Speak and Act

Siyin Wang, Wenyi Yu, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Lu Lu, Yuxuan Wang, Chao Zhang

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 5 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
use SA-MoE (attention-connected experts) instead of one dense model (ablation)ELLSA · Llama Questions S2Taccuracy (%): 62.7 -> 74.7Improved
use SA-MoE instead of dense model initialized from action expert (ablation)ELLSA · LIBERO-LONGsuccess rate (%): 60.6 -> 84.4Improved
SA-MoE vs dense from speech expert (unfamiliar action modality) (ablation)ELLSA · LIBERO-SPATIALsuccess rate (%): 0.2 -> 90.8Improved
integrate speech and action experts via SA-MoE vs speech expert aloneELLSA · TriviaQA S2Taccuracy (%): 55.9 -> 45.2Hurt
integrate via SA-MoE vs action expert aloneELLSA · LIBERO-LONGsuccess rate (%): 94.0 -> 84.4Hurt
speak while acting (concurrent generation)ELLSA · LIBERO-LONGsuccess rate (%): 84.4 -> 73.2Hurt
speak while actingELLSA · TriviaQA S2Taccuracy (%): 45.2 -> 35.1Hurt
ELLSA full-duplex speech-to-speech vs Freeze-OmniELLSA · Llama Questions S2Saccuracy (%): 56.2 -> 70.0Improved
ELLSA vs Freeze-Omni text-mode open-ended chatELLSA · AlpacaEval S2TGPTScore: 3.90 -> 3.09Hurt
ELLSA speech-conditioned VLA vs pi0-FASTELLSA · LIBERO averagesuccess rate (%): 85.5 -> 89.4Improved
shorter time block (0.48 s vs 1 s) (ablation)action expert · LIBEROsuccess rateHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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