Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2606. 16484v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) hold great potential for medicine, as they inherit knowledge from LLM and allow multiple data modalities to be integrated, analysed and interpreted in natural language.
arXiv:2606. 16286v1 Announce Type: cross Abstract: Flow Matching (FM) is a powerful approach for behavior cloning in multimodal action spaces [Jiang et al.
arXiv:2606. 16388v1 Announce Type: new Abstract: High-dimensional incomplete (HDI) tensors are widely used in traffic and climate applications, but sparse observations make accurate completion difficult.
arXiv:2606. 16408v1 Announce Type: new Abstract: We introduce MUNI, an end-to-end multimodal latent diffusion framework for any-to-any generation that unifies subset-conditioned cross-modal generation and unconditional joint sampling through a shared stochastic latent.
Remote sensing vision-language models have advanced Earth observation understanding, but most existing work remains centered on RGB imagery, leaving the complementary information in infrared data underexplored. Infrared images provide distinctive cues, including thermal intensity structures, object boundaries, and illumination-invariant scene features, which can enrich visual-language learning beyond conventional RGB observations.
Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins. These models are built through post-training, yet how each stage shapes reasoning and generalization remains poorly understood.
arXiv:2512. 10966v3 Announce Type: replace-cross Abstract: Accurate and early diagnosis of Alzheimer's disease (AD) is critical for effective intervention and requires integrating complementary information from multimodal neuroimaging data.
arXiv:2606. 14375v1 Announce Type: cross Abstract: Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules.
arXiv:2606. 13657v2 Announce Type: replace Abstract: On-policy distillation (\textsc{OPD}) has recently become a prominent post-training recipe by combining two desirable ingredients: on-policy student trajectories and dense teacher supervision.
arXiv:2606. 14697v1 Announce Type: cross Abstract: Building trustworthy medical multimodal large language models (MLLMs) is critical for reliable clinical decision support.
arXiv:2604. 21335v3 Announce Type: replace Abstract: Transformer inference often requires a large KV cache, especially for long-context language modeling and multimodal generation.
arXiv:2510. 02695v3 Announce Type: replace-cross Abstract: In safety-critical domains where online data collection is infeasible, offline reinforcement learning (RL) is attractive only if policies achieve high returns without catastrophic lower-tail risk.
arXiv:2606. 13896v1 Announce Type: cross Abstract: Self-supervised geospatial foundation models (GeoFMs) learn transferable representations from remote sensing data, but their downstream behavior is difficult to characterize.
arXiv:2606. 12817v2 Announce Type: replace Abstract: Understanding the digital world on mobile devices is shifting from static UI perception to dynamic action comprehension.
arXiv:2606. 14169v1 Announce Type: new Abstract: Raman spectroscopy provides label-free, chemically specific characterization of biological systems and has become an important tool for cancer diagnosis, molecular subtyping, microbiological identification, and intraoperative decision support.
arXiv:2606. 12994v2 Announce Type: replace Abstract: Data-driven engineering design is constrained by the lack of large-scale 3D datasets that pair geometry with physics-based performance labels.
arXiv:2508. 18166v5 Announce Type: replace-cross Abstract: Modern app store recommender systems struggle with multiple-category apps, as traditional taxonomies fail to capture overlapping semantics, leading to suboptimal personalization.
arXiv:2606. 14391v1 Announce Type: cross Abstract: Despite advances in large-scale Automatic Speech Recognition (ASR), disfluent speech remains challenging, as state-of-the-art systems are often optimized to omit disfluencies, leading to information loss and hallucinations.
arXiv:2505. 16120v3 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) has reshaped agent systems.
arXiv:2606. 14238v1 Announce Type: cross Abstract: Safety certification of Vision-Language-Action (VLA) driving planners under ISO 21448 (SOTIF) rests on an Operational Design Domain (ODD) specification that answers two complementary questions: when does the planner start to fail, and how severely does it fail once it does?