forked from kent/consciousness
Two research documents: latent-reasoning-integration-plan.md: Synthesizes 10+ papers on latent reasoning, identifies which approaches work with finetuning (vs requiring pretraining from scratch), and maps them to our APOLLO-Mini training pipeline. pause-tokens-gdn-recurrence.md: Explores the connection between token-based latent reasoning and GDN's internal recurrence. Key insight: pause tokens on Qwen 3.5 trigger both forward passes AND recurrent state updates, giving double benefit. Co-Authored-By: Proof of Concept <poc@bcachefs.org> |
||
|---|---|---|
| .. | ||
| v0 | ||
| apollo-paper-analysis.md | ||
| context-frozen-training.md | ||
| gdn-gradient-flow.md | ||
| gradient-flow-frozen-context.md | ||
| hogwild-convergence.md | ||
| OPEN-QUESTIONS.md | ||
| pause-tokens-gdn-recurrence.md | ||
| practical-intuitions.md | ||
| steering-vectors-bridge.md | ||
| SUMMARY.md | ||
| task-vectors-model-merging.md | ||