arXiv:2603. 14405v2 Announce Type: replace-cross Abstract: Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for scientific discovery.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2607. 20557v1 Announce Type: cross Abstract: Scientific discovery is increasingly shifting from isolated disciplines to multi-domain reasoning, and AI for science faces a similar transition.
MolEmb is a lightweight framework that adapts multimodal large language models (MLLMs) to serve as general molecular embedding models. By aligning molecular profiles with textual descriptions in a shared embedding space using a bidirectional contrastive objective, MolEmb produces embeddings conditioned on both a molecular profile and a natural‑language semantic context. The model performs competitively on molecular property prediction and enables cross‑modal molecule‑text retrieval, while the newly introduced MolCAR benchmark demonstrates that context‑aware molecular embedding is largely a data property of the supervision.
arXiv:2604. 22823v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities.
arXiv:2607. 08839v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference.
arXiv:2608. 02769v1 Announce Type: cross Abstract: Multimodal supervised learning seeks to leverage multiple heterogeneous data sources to improve predictive performance.
MoEMB introduces a mixture‑of‑experts (MoE) approach to scale universal multimodal embeddings (UME) without increasing the size of the output vector or relying on autoregressive decoding. By expanding encoder capacity along the expert axis, MoEMB achieves state‑of‑the‑art performance on MMEB‑V2 and MRMR benchmarks with only 3 B active parameters, outperforming TTE‑based methods that use more than four times as many active parameters and require significantly more compute. The paper also presents the first comprehensive study of adaptive computation for MoE‑based embeddings, exploring training‑time and inference‑time strategies to further improve efficiency for large‑scale retrieval and recommendation systems.