The paper introduces ModalShare, a bandwidth allocation method for multimodal split learning that assigns each modality a keep‑ratio based on its Shapley contribution score. Unlike existing compression schemes that split the uplink budget proportionally to activation size, ModalShare explicitly optimizes the split across modalities, requiring no extra uplink traffic or client computation. Experiments on CREMA‑D and MVSA datasets show that ModalShare improves accuracy by 12.4–15.4 percentage points over equal keep‑ratios under a 5× compression budget, outperforming three compressors across multiple datasets and budgets.
arXiv:2508. 06692v2 Announce Type: replace Abstract: Federated learning systems typically allocate gradient compression by link speed.
The paper introduces EMMI, a framework that enables communication‑efficient inference of multimodal large language models (MLLMs) on edge devices. EMMI encodes each sensor modality separately, fuses the representations, and compresses them into a compact latent vector that is transmitted to a server for high‑capacity reasoning. Experiments on a multimodal benchmark show that EMMI can cut the communication payload by 32× while keeping accuracy comparable, achieving up to a 3.4× reduction in end‑to‑end inference latency under bandwidth‑constrained conditions.
arXiv:2607. 06651v1 Announce Type: new Abstract: Federated learning (FL) over mobile and edge devices increasingly involves multimodal models in which clients differ in both sensing capability and computational capacity.
arXiv:2608.23018v1 Announce Type: cross Abstract: Federated fine-tuning of on-device large language models (LLMs) faces a significant computing burden. To overcome this limitation, split learning (SL...
The paper introduces GaugeLasso, a method that applies symmetric group‑lasso penalties to transformer channels during training, enabling entire tensor slices to be zeroed out while maintaining dense tensors for GPU efficiency. By calibrating channel penalties based on inference utility per compute, the network self‑organizes into depth‑dependent structural profiles that can be dramatically smaller than the original architecture, achieving up to 255‑fold compression on a polynomial division task and outperforming hand‑designed baselines on language modeling and autoencoding benchmarks. The approach also accelerates training and reveals over‑provisioned axes that guide subsequent design iterations.
arXiv:2608. 09250v1 Announce Type: new Abstract: Federated learning (FL) must serve devices with varying computational capabilities.
arXiv:2607. 18343v1 Announce Type: cross Abstract: Federated fine-tuning is bottlenecked by communication: FedAvg and pseudo-gradient schemes transmit a payload that scales with the model, and gradient compression shrinks it by only a constant factor.
arXiv:2606. 09853v1 Announce Type: new Abstract: A central objective in multimodal learning is to capture synergy: task-relevant information that arises only from the joint use of multiple modalities, and is not available from any single modality alone.
arXiv:2607. 25669v1 Announce Type: new Abstract: Emerging Omni-modal Large Language Models (OmniLLMs) enable unified understanding of text, audio, and video, but their long audio-video token sequences introduce substantial memory and inference costs.
arXiv:2605.26513v2 Announce Type: replace Abstract: Even balanced multimodal learning methods do not consistently translate additional modalities into better regression performance. To understand thi...
arXiv:2606. 27866v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models scale model ability with sparsely activated experts, making this architecture a standard recipe for modern large models.
arXiv:2606. 21337v2 Announce Type: replace Abstract: Raw multimodal streams are abundant but noisy, redundant, and unaligned with any particular training objective.