myWiki/raw/papers/hazare-dcgwm-2026.md

title, source_id, authors, affiliations, date, categories, note, url

title	source_id	authors	affiliations	date	categories	note	url
Dual-Channel Grounded World Modeling (DCGWM)	arXiv:2606.18688v1	Akshay Hazare	Independent Researcher	2026-06-17	cs.LG cs.AI	Position paper. Experimental validation in progress.	https://arxiv.org/abs/2606.18688v1

Dual-Channel Grounded World Modeling (DCGWM)

Authors: Akshay Hazare (Independent) arXiv: 2606.18688v1 | Date: 2026-06-17 Categories: cs.LG, cs.AI Position paper — experimental validation ongoing

Abstract

Joint Embedding Predictive Architectures (JEPAs) are a leading approach to world model representation learning. We identify a failure mode in JEPA-based world models grounded against two qualitatively distinct external signals: physical dynamics (sparse, high-magnitude, constraint-satisfying gradient corrections) and social-behavioral dynamics (diffuse, distribution-matching corrections). We term this Objective Interference Collapse (OIC): joint learning in a shared latent space causes the dominant channel to systematically collapse the subordinate channel's representational subspace, in a manner not resolvable by loss weighting alone.

We propose Dual-Channel Grounded World Modeling (DCGWM), designed to structurally prevent OIC through a partitioned latent space (Z_p ⊕ Z_b) with inward-only gradient flow. The Physical Grounding Channel updates only Z_p via VICReg-style alignment; the Social-Behavioral Grounding Channel updates only Z_b via alignment to emergent multi-agent simulation trajectories. An Inter-Channel Interface Module couples subspaces at the task level without cross-subspace gradients. An Asymmetric Grounding Adherence Loss penalizes rollout drift with a hard hinge for physical violations and a soft KL for behavioral divergence. A Generative Rendering Layer is architecturally isolated from the latent world model.

Three theoretical results: the partition removes the gradient-interference pathway; each grounded subspace inherits anti-collapse guarantees; generative isolation is necessary under stated assumptions.

Key Contributions

1. Objective Interference Collapse: Formalization of a new collapse mode — when two grounding signals with incompatible statistical structures share a latent space
2. DCGWM Architecture: Partitioned latent space + inward-only gradient flow + separated grounding channels
3. Asymmetric Grounding Adherence Loss (L_AGA): First loss for rollout drift under heterogeneous grounding with incompatible tolerance structures
4. Isolation Necessity Theorem: Under assumptions A1-A2, any α > 0 generative gradient causes world model drift
5. LLM World Modeling Critique: NTP-trained LLMs face inherent subspace collapse that DCGWM avoids by design

Key Concepts

• objective-interference-collapse — The new collapse mode this paper identifies
• dcgwm — The architecture
• inward-only-gradient-flow — The key separation mechanism
• asymmetric-grounding-adherence-loss — Asymmetric rollout drift penalty
• rollout-drift — Multi-step prediction error accumulation
• isolation-necessity-theorem — Formal generative isolation result