repoGitHubTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago
Xiaohao-Liu/Awesome-Multi-Token-Prediction
A curated list of papers, tools, and resources on Multi-Token Prediction (MTP) and related techniques in Large Language Models (LLMs), Speech-Language Models (SLMs), and more.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Using embeddings to predict spoken word duration and pitch in Mandarin monosyllabic words →
- PossiblePossibly related (embedding) · 51%From Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond →
- PossiblePossibly related (embedding) · 51%LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training →
- PossiblePossibly related (embedding) · 50%A Sovereign, Open-Source Foundation Model for German and English →
- PossiblePossibly related (embedding) · 49%BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech →
Implements
paperUsing embeddings to predict spoken word duration and pitch in Mandarin monosyllabic wordspaperFrom Tokens to States: LLMs as a Special Case of World Models and the Continuous Path BeyondpaperLeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-TrainingpaperA Sovereign, Open-Source Foundation Model for German and EnglishpaperBlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech
Related across the graph
paperBlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching SpeechpaperUsing embeddings to predict spoken word duration and pitch in Mandarin monosyllabic wordspaperA Sovereign, Open-Source Foundation Model for German and EnglishpaperLeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-TrainingpaperFrom Tokens to States: LLMs as a Special Case of World Models and the Continuous Path Beyond