arXiv (All)
open access
LS-AR: Future-Predictive Latent Steering in Autoregressive LLMs
Standard autoregressive (AR) models process high-level task instructions, state history, and transient tokens within a single shared sequence of tokens. Consequently, they lack the architectural mechanisms needed to isolate macro-objectives from context noise. To overcome this single-channel limitat
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Autoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM Generation#1327631
- Prediction Error Convergence (PEC) Protocol for Realizing Intersubjective Rest: A Load Minimization Theory (LMT) Framework#83489
- Uncovering Uncontrolled Repetition through Residual Stream Dynamics#1143403
- RL Post-Training Diffusion Language Models Along Their Own Generation Paths#1342142
- AVL-JEPA: Preventing Causal Dynamics Information Collapse In Joint Embedding Predictive Architecture World Models#1188298
Record · ID 1187771
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive