LS-AR: Future-Predictive Latent Steering in Autoregressive LLMs

arXiv:2610.03093 · cs.LG · Submitted 2026-10-02 · Read on arXiv

cs.LG

Submitted: 2026-10-02

Updated: 2026-10-02

Code: https://github.com/agupta1024/future-conditional-llms

Terminology

• Steering — 1× in this paper · explained in 2 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
• Extending Context Window of Large Language Models via Positional Interpolation
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• Generating Long Sequences with Sparse Transformers
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Efficiently Modeling Long Sequences with Structured State Spaces
• ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
• LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures
• Landmark Attention: Random-Access Infinite Context Length for Transformers
• Needle in the Haystack for Memory Based Large Language Models
• Counting Ability of Large Language Models and Impact of Tokenization
• Universal and Transferable Adversarial Attacks on Aligned Language Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks