Multimodal reinforcement learning agents must fuse signals with vastly different noise profiles—yet existing architectures, whether monolithic (π0, DreamerV3) or modular (MSDP, VTDexManip), allow noise from unreliable modalities to contaminate reliable ones at the point of fusion. We propose filter before mixing: each modality’s representation is independently refined by a per-modality Flow Matching module before spectral-domain fusion via a Fourier Neural Operator (FNO) with a residual gate ensuring that refinement is never harmful. The resulting architecture, FreamerV1 (Filter-before-mixing dreamer), has 93M parameters (0.4M trainable). On MiniGrid, FreamerV1 reaches 87.7 ± 8.2% (3 seeds) at 5000 episodes, while the encoder-only baseline degrades to 78% due to catastrophic forgetting. With OGM-GE (On-the-fly Gradient Modulation) for adaptive per-modality gate control, FreamerV1 achieves an 8.0% relative improvement in success rate over manual tuning with halved seed-to-seed variance (three seeds). On Crafter (no language modality), it achieves an 11.7% relative improvement over DreamerV3 in the official Crafter score (geometric mean of 22 achievement success rates; 10 seeds). On PAMAP2 wearable sensors—where no pretrained encoder exists—the foundation encoder achieves 2.4× higher reward and 16× lower variance than a vanilla MLP, confirming that the filter-before-mixing advantage grows with encoder noise.
Tsuyoshi Okita (Fri,) studied this question.