状态: 实验性
世界模型
深度感知世界模型(DAWM):世界模型实验、阶段诊断、失效分析与当前信念更新。
范围
一条实验性方向,整合自早期 Octoryn Research 的工作,通过逐阶段诊断研究深度感知世界模型——把回归视为一连串被否证的假设,而非单一的训练失败。
本方向的研究项目
- 状态: 实验性DAWM——深度感知世界模型
世界模型实验、阶段诊断与失效分析,把回归视为一连串被否证的假设,而非单一的训练失败。
开放问题
- RQ-002证据收集中DAWM 第 7 阶段的哪些回归属于架构性问题,而非调参噪声?
发表
- Frozen-backbone slot binding exceeds feature clustering, with a characterized ceiling
- The Grounding Seam Failure: useful relations are not discovered from features
- DAWM: State over Token — a research charter with falsifiers
- DAWM State Contract: Observation to Event to Fluent
- Catalog of mechanism and boundary findings from a structured-state reasoning program
- A deflated box-derived evaluation yardstick, and a (later-overturned) negative for frozen-backbone slot-binding
- Anti-collapse penalties transfer to real data, and a second collapse mode at the decoder in slot-based object discovery
- Cross-Rendering Semantic Binding in an Engineered Small-Cell Schema (Mechanism Findings)
- DAWM Phase 3: selective persistence, contradiction handling, and learned abstain
- Soft cross-rendering convergence vs. graph-verified carrier-independence, and the value-erased-schema control boundary
- DAWM Phase 10: controlled small-cell integration coherence (preliminary)
- Controlled Symbolic Rendering-Invariance via Independent Learned Non-Text Parsers
- The slot-stationarity collapse boundary in learned variable-cardinality semantic schemas — a negative result
- Learned cursor routing under activation-graph cells: a negative-then-repair study of multi-candidate disambiguation, abstain stability, and deferred commitment
- DAWM Phase 9: cost-aware learned routing and budget-gated rollout
- DAWM Phase 7: multi-track consolidation
- Dual-channel reasoning state and a semantic-depth bridge for contradiction handling