3 dépôts
Flow-matching architectures specifically designed to generate text via continuous embeddings.
Distinct from Flow-Matching Frameworks: Specializes flow-matching for text-token generation rather than the common image-based application.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Continuous Text Generation. Refine with filters or upvote what's useful.
This project is a machine learning research automation system designed to manage the full research lifecycle, from idea discovery to final paper submission. It utilizes markdown-based skill templates to execute autonomous research tasks and manage iterative loops of deep review and experimentation. The system distinguishes itself through integrated capabilities for academic communication and integrity auditing. It can automate the generation of LaTeX papers, conference slide decks, and evidence-grounded peer review rebuttals. To ensure rigor, it employs cross-model review routing and adversar
Transforms noise into clean embeddings using flow matching for continuous text generation.
AI NovelGenerator est un outil pour générer de la fiction longue en utilisant de grands modèles de langage. Il fonctionne comme un architecte narratif et un assistant d'écriture, automatisant la création de romans multi-chapitres tout en gérant la structure globale de l'histoire et le suivi des personnages. Le projet se distingue par un système de récupération de contexte sémantique et un vérificateur de cohérence d'histoire par IA. Ces outils utilisent la recherche sémantique pour rappeler des détails spécifiques de l'histoire à partir des chapitres précédents et scanner le texte généré pour détecter des contradictions d'intrigue ou des incohérences comportementales. Le système couvre un cycle de vie narratif complet, incluant la conception des fondations de l'histoire, le worldbuilding et la planification de la structure du roman. Il utilise un pipeline multi-étapes pour rédiger des chapitres cohérents et intègre un atelier de workflow créatif pour gérer les paramètres et la relecture.
Provides automated scanning of generated text to identify logical plot contradictions and character inconsistencies.
ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,
ExecuTorch continues text generation from a specific point in the cache, enabling stateful continuation.