The paper introduces causal‑fate dynamics, a framework describing how influence generated in a system can be realized, remain latent, or be transformed by later dynamics. It presents an exact finite‑transport representation for these processes and applies the concept to three domains: a connectome‑constrained model of *Caenorhabditis elegans* suggesting unresolved neuronal influence may persist, an analysis of Internet routing showing that cross‑observer history retains predictive power beyond local state, and a Transformer architecture that transports and selectively realizes latent contextual influence while preserving language‑modeling performance. These studies collectively illustrate how unrealized influence can be modeled, observed, and harnessed in computational systems.
arXiv:2606. 05194v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being deployed to make decisions that require trading off near-term gains against long-term consequences, yet little is known about how they internally represent or resolve these tradeoffs.
arXiv:2606. 09287v1 Announce Type: new Abstract: Understanding how transformer representations evolve across layers, not merely what they encode, remains an open problem in mechanistic interpretability.
arXiv:2609.16752v1 Announce Type: new Abstract: Cognitive Field Theory (CFT) proposes that cognition arises from memory-dressed collective dynamics that generate a persistent macroscopic cognitive fi...
arXiv:2607. 11958v1 Announce Type: new Abstract: Under the free energy principle, a predictive system does not observe reality directly; it maintains a generative model of the world and experiences that model's best current hypothesis.
arXiv:2609.36063v1 Announce Type: cross Abstract: Neural Combinatorial Optimization (NCO) has achieved strong empirical success, yet the internal mechanisms driving model decisions remain largely une...
BrainDyn is a graph ordinary differential equation (ODE) network that models brain activity as coordinated patterns across connected regions. It uses a cellular sheaf with dynamic restriction maps to mediate region-to-region communication through learned linear transformations, rather than the standard shared feature space and scalar summation of message‑passing networks. Evaluated on resting‑state fMRI, EEG, and simulated NEST data, BrainDyn outperforms competing models in multi‑region forecasting, autoregressive generation of brain transients, and prediction of altered transients after controlled perturbations, while its learned features are expressive, interpretable, and biologically aligned.
arXiv:2601. 21135v2 Announce Type: replace Abstract: Temporal causal representation learning methods assume that causal mechanisms switch instantaneously between discrete domains, yet real-world systems often exhibit continuous mechanism transitions.
arXiv:2603. 16689v2 Announce Type: replace Abstract: Next-token predictors often appear to develop internal representations of the latent world and its rules.
arXiv:2608. 12334v1 Announce Type: cross Abstract: Despite the impressive multilingual capabilities of Large Language Models, the latent dynamics dictating language selection remain poorly understood.
arXiv:2604. 17121v3 Announce Type: replace Abstract: Transformers encode structure in sequences via an expanding contextual history.
The paper studies when joint-embedding predictive architectures (JEPAs) can recover underlying causal states from high‑dimensional observations. It introduces a latent variable model where observations arise from causal states with action‑conditioned dynamics, and proposes an information‑theoretic objective that maximizes conditional likelihood while preserving state entropy. The authors prove identifiability conditions—particularly sufficient action‑induced variation—and instantiate the objective as an action‑modulated Gaussian additive‑noise model (A‑JEPA), demonstrating theoretical and empirical success in synthetic and visual benchmarks.
arXiv:2609.13899v1 Announce Type: cross Abstract: The BabyLM challenge measures how much language a model can learn from developmentally-plausible, child-scale data rather than internet-scale corpora...