Latent Trajectory Discrimination for AI-Generated Text Detection
Most existing approaches to AI-Generated Text Detection (AIGTD) treat documents as static objects and base their decisions on aggregate statistics or globally compressed embeddings. However, this perspective overlooks the inherently dynamic nature of autoregressive generation, where content evolves progressively through the latent space. In this paper, we reformulate AIGTD as the problem of distinguishing between latent generation trajectories. Instead of relying on static representations, we model how textual representations evolve across the sequence. To this end, we propose Geometric Trajec
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) · 54%DiffusionGemma: 4x faster text generation →
- LinkedLinked via arxiv author · 85%Gianluca Bonifazi →
“Latent Trajectory Discrimination for AI-Generated Text Detection”
- LinkedLinked via arxiv author · 85%Christopher Buratti →
“Latent Trajectory Discrimination for AI-Generated Text Detection”
- LinkedLinked via arxiv author · 85%Michele Marchetti →
“Latent Trajectory Discrimination for AI-Generated Text Detection”
- LinkedLinked via arxiv author · 85%Federica Parlapiano →
“Latent Trajectory Discrimination for AI-Generated Text Detection”
- LinkedLinked via arxiv author · 85%Giulia Quaglieri →
“Latent Trajectory Discrimination for AI-Generated Text Detection”
- LinkedLinked via arxiv author · 85%Davide Traini →
“Latent Trajectory Discrimination for AI-Generated Text Detection”
- LinkedLinked via arxiv author · 85%Domenico Ursino →
“Latent Trajectory Discrimination for AI-Generated Text Detection”