Photonic computing has emerged as a promising substrate for accelerating the dense linear-algebra operations at the heart of AI, but its adoption for large Transformer models remains in its infancy. In supporting these massive models, we identify two key bottlenecks: (1) costly electro-optic conversions and data-movement overheads that erode energy efficiency as model sizes scale; (2) a mismatch between limited on-chip photonic resources and the scale of Transformer workloads, which forces frequent reuse of photonic tensor cores and dilutes throughput gains. To address these challenges, we introduce a hardware–software co-design framework. First, we propose Lighten, a PTC-aware compression flow that post-hoc decomposes each Transformer weight matrix into a low-rank component plus a structured sparse component aligned to photonic tensor-core granularity, all without lengthy retraining. Second, we present ENLighten, a reconfigurable photonic accelerator architecture featuring dynamically adaptive tensor cores, driven by a broadband light redistribution, for fine-grained sparsity support and full power gating of inactive parts. On ImageNet, Lighten prunes Base-scale vision transformer by 50% with a ~1% accuracy drop after only 3 epochs of fine-tuning within 1 hour, and when deployed on ENLighten it achieves a $2.5 \times$ improvement in energy-delay product over the state-of-the-art photonic Transformer accelerator.

Electromagnetic field simulation is central to designing, optimizing, and validating photonic devices and circuits. However, costly computation associated with numerical simulation poses a significant bottleneck, hindering scalability and turnaround time in the photonic circuit design process. Neural operators offer a promising alternative, but existing SOTA approaches, Neurolight, struggle with predicting high-fidelity fields for real-world complicated photonic devices, with the best reported 0.38 normalized mean absolute error in Neurolight. The interplays of highly complex light-matter interaction, e.g., scattering and resonance, sensitivity to local structure details, non-uniform learning complexity for full-domain simulation, and rich frequency information, contribute to the failure of existing neural PDE solvers. In this work, we boost the prediction fidelity to an unprecedented level for simulating complex photonic devices with a novel operator design driven by the above challenges. We propose a novel cross-axis factorized PACE operator with a strong long-distance modeling capacity to connect the full-domain complex field pattern with local device structures. Inspired by human learning, we further divide and conquer the simulation task for extremely hard cases into two progressively easy tasks, with a first-stage model learning an initial solution refined by a second model. On various complicated photonic device benchmarks, we demonstrate one sole PACE model is capable of achieving 73% lower error with 50% fewer parameters compared with various recent ML for PDE solvers. The two-stage setup further advances high-fidelity simulation for even more intricate cases. In terms of runtime, PACE demonstrates 154-577x and 11.8-12x simulation speedup over numerical solver using scipy or highly-optimized pardiso solver, respectively. We open-sourced the code and *complicated* optical device dataset at [PACE-Light](https://github.com/zhuhanqing/PACE-Light).