2026-01-103 saved articles | Back | Library |
|---|
| Article | Read |
|---|---|
| GitHub - yifanzhang-pro/deep-delta-learning: Official Project Page for Deep Delta Learning (https://arxiv.org/abs/2601.00417) Official Project Page for Deep Delta Learning (https://arxiv.org/abs/2601.00417) - yifanzhang-pro/deep-delta-learning | |
| Deep Delta Learning Transformer residual streams evolve by additive accumulation: each layer appends a feature update to a shared hidden state, but has no direct mechanism for replacing content that has become obsolete or conflicting. We introduce Deep Delta Learning (DDL), a residual update rule that preserves the identity path while giving every layer the ability to selectively rewrite residual content. DDL reads the current state along a learned direction, compares it with a learned target value, and writes back | |
| GitHub - parcadei/Continuous-Claude-v3: Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows. Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows. - parcadei/Continuous-... |