Latent Reasoning Does Not Lack Signal, It Lacks Invariance: Subspace-Constrained Refinement for Robust Reasoning
cs.LG, cs.AI, cs.CG
Submitted: 2026-06-28
Updated: 2026-11-06
Terminology
Sources
- Invariant Risk Minimization
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- The Llama 3 Herd of Models
- Training Large Language Models to Reason in a Continuous Latent Space
- TRGP: Trust Region Gradient Projection for Continual Learning
- Gradient Projection Memory for Continual Learning
- Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
- Steering Language Models With Activation Engineering
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis