mlsanityData to 14 Oct 2026

Full-duplex Spoken Language Modeling with Discrete Diffusion

arXiv 2610.17780 ↗First posted 13 Oct 2026cs.CLcited by 0

On the map: Diffusion models → Audio, speech and music also fits: Discrete and text diffusion

Abstract (arXiv)

We introduce Diffuplex, a full-duplex spoken language model based on discrete diffusion that achieves an unprecedented balance between linguistic intelligence and response efficiency. With thinking mode, Diffuplex delivers 13.0 tokens per forward pass, reaching an average of 1872 tokens per second and substantially surpassing the frontier autoregressive (AR) models in decoding speed. Without thinking, Diffuplex matches the first-audio latency of existing full-duplex models while achieving markedly stronger linguistic intelligence. This capability is enabled by separating when to say from what to say at the training level, rather than compressing both into a single autoregressive timeline. During inference, Diffuplex continuously tracks the user speech through an AR interaction policy, while independently generating and refining response content through parallel diffusion. Consequently, semantic computation is no longer bounded by the perception audio frame rate, allowing intelligence and responsiveness to improve simultaneously. Taken together, these results establish a new paradigm for spoken agents that can sustain real-time dialogue while devoting parallel computation to intelligent response generation. Training code and checkpoints will be avaliable soon.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 39 of its 50 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

39 of 50 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model14 Jul
  2. 2025DIFFA: Large Language Diffusion Models Can Listen and Understand24 Jul
  3. 2022TransFusion: Transcribing Speech with Multinomial Diffusion14 Oct

Other references · 36

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2024GPT-4o System Cardcited by 4,588
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  5. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  6. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  7. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  8. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  9. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  10. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  11. 2023SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilitiescited by 529
  12. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 521
24 more
  1. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 360
  2. 2024GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbotcited by 224
  3. 2025Generalizing Verifiable Instruction Followingcited by 194
  4. 2025MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMscited by 180
  5. 2024Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLMcited by 141
  6. 2025Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilitiescited by 100
  7. 2023Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMcited by 94
  8. 2026PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Modelscited by 63
  9. 2024OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversationcited by 60
  10. 2026Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluencycited by 37
  11. 2025SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Modelcited by 34
  12. 2026Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decodingcited by 24
  13. 2026X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMscited by 16
  14. 2026The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoningcited by 6
  15. 2025End-to-end Listen, Look, Speak and Actcited by 5
  16. 2026Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMscited by 5
  17. 2026NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilitiescited by 4
  18. 2026DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understandingcited by 3
  19. 2026Decoupling Conversational Dynamics in Full-Duplex Spoken Models through Reinforcement Learningcited by 3
  20. 2025Whisfusion: Parallel ASR Decoding with Masked Diffusioncited by 2
  21. 2026Liberating LLM Capabilities in Full-Duplex Speech Modelscited by 2
  22. 2026ParaASR: Multi-Token Prediction for Fast and Long-Context LLM-Based Speech Recognitioncited by 2
  23. 2026MDM-ASR: Bridging Accuracy and Efficiency in ASR with Diffusion-Based Non-Autoregressive Decodingcited by 1
  24. 2026Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DiffuPlex: Accelerating Full-Duplex Spoken Dialog Models via Rolling Masked Diffusion
  2. 2026BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM
  3. 2026RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can
  4. 2026Unit-Based Agent for Semi-Cascaded Full-Duplex Dialogue Systems
  5. 2025Discrete Diffusion in Large Language and Multimodal Models: A Survey
  6. 2024Enabling Real-Time Conversations with Minimal Training Costs
  7. 2025From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training
  8. 2024SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation