Multimodal Foundation Model

Fine-tuning foundation models for Earth Observation is computationally expensive, with high training time and memory demands for both training and deployment. Parameter-efficient methods reduce training cost but retain full inference complexity, while post-hoc compression optimizes inference only after costly full fine-tuning. We introduce SIMPLER, a pre-fine-tuning architecture selection method that reduces inference and deployment costs by identifying an effective model depth before adaptation. SIMPLER exploits stabilization of representations in deeper layers of pre-trained vision transformers: it computes layer-wise representation similarity on unlabeled task data and applies an automated scoring function to select redundant layers, with no gradients, magnitude heuristics, or hyperparameter tuning required. On Prithvi-EO-2, SIMPLER prunes up to 79% of parameters while retaining 94% of baseline performance, yielding a 2.1x training speedup and 2.6x inference speedup. The method generalizes to TerraMind (a multimodal EO foundation model) and ImageNet-pretrained ViT-MAE, demonstrating applicability across tasks, architectures, and spectral modalities. Code is available at https://gitlab.citius.gal/hpc4rs/simpler.

While recent multimodal large language models (MLLMs) have made impressive strides, they predominantly employ a conventional autoregressive architecture as their backbone, leaving significant room to explore effective and efficient alternatives in architectural design. Concurrently, recent studies have successfully applied discrete diffusion models to various domains, such as visual understanding and image generation, revealing their considerable potential as a promising backbone for multimodal systems. Drawing inspiration from these pioneering studies, we introduce Omni-Diffusion, the first any-to-any multimodal language model built entirely on mask-based discrete diffusion models, which unifies understanding and generation across text, speech, and images. Omni-Diffusion employs a unified mask-based discrete diffusion model to directly capture the joint distribution over discrete multimodal tokens. This approach supports not only bimodal tasks but also more complex scenarios involving multiple modalities. On a diverse set of benchmarks, our method outperforms or performs on par with existing multimodal systems that process two or more modalities, highlighting the significant promise of diffusion models in powering the next generation of multimodal foundation models. Project webpage: https://omni-diffusion.github.io.

The emergence of audio-visual foundation models underscores the importance of reliably assessing their multi-modal understanding. The VGGSound dataset is commonly used as a benchmark for evaluation audio-visual classification. However, our analysis identifies several limitations of VGGSound, including incomplete labelling, partially overlapping classes, and misaligned modalities. These lead to distorted evaluations of auditory and visual capabilities. To address these limitations, we introduce VGGSounder, a comprehensively re-annotated, multi-label test set that extends VGGSound and is specifically designed to evaluate audio-visual foundation models. VGGSounder features detailed modality annotations, enabling precise analyses of modality-specific performance. Furthermore, we reveal model limitations by analysing performance degradation when adding another input modality with our new modality confusion metric.

Conventional forecasting methods are trained end-to-end on unimodal time series, which limits their ability to exploit textual information and undermines their generalization in data-scarce scenarios. Recently, large language models (LLMs) and time series foundation models (TSFMs) have demonstrated powerful capabilities in complex textual reasoning and zero-shot temporal modeling, respectively. Integrating these strengths to construct a multimodal time series foundation model that jointly leverages temporal and textual information for zero-shot future inference has emerged as a promising research direction. However, the scarcity of large-scale, high-quality multimodal datasets remains a fundamental obstacle. To address this challenge, we propose ChronoSteer, a decoupled agentic framework that learns cross-modal alignment from synthetic paired supervision. Specifically, a pretrained LLM first converts textual events into revision instructions that steer the initial unimodal prediction produced by a frozen TSFM. These revision instructions form an intermediate instruction space that bridges the semantic gap between text and time series while fully leveraging pretrained knowledge. Technically, the instructions are discretized into a compact codebook of instruction anchors, effectively mitigating semantic divergence while reducing the cost of dataset construction. Finally, we adopt a two-stage training strategy to recover the fine-grained magnitude information lost during discretization. Furthermore, we release a leakage-controlled multimodal benchmark constructed with temporal separation and textual context available before the prediction window. When paired with an LLM and trained on synthetic cross-modal alignment data, ChronoSteer achieves a 25.8% improvement in zero-shot prediction accuracy over its unimodal backbone, and outperforms prior state-of-the-art unimodal and multimodal ...