Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2605. 06317v4 Announce Type: replace-cross Abstract: Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulation and limits efficiency.
arXiv:2606. 08970v1 Announce Type: new Abstract: Vision-language models (VLMs) with varying performance and resource requirements are widely deployed, making it difficult for users to select the most appropriate one among numerous VLM candidates.
arXiv:2606. 07658v1 Announce Type: cross Abstract: Maximal safe resection is the primary objective in glioma surgery.
arXiv:2605. 30226v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for grounding visual-language understanding into real-world robotic manipulation.
arXiv:2411. 19504v2 Announce Type: replace Abstract: The advance of large language models (LLMs) has unlocked great opportunities in complex multi-modal data management tasks, particularly in question answering (QA) over complicated multi-table relational data.
arXiv:2606. 07591v1 Announce Type: cross Abstract: AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify.
arXiv:2606. 08777v1 Announce Type: cross Abstract: Visual Language Models (VLMs) are known to produce hallucinated predictions that are not grounded in visual evidence, yet existing approaches lack a principled understanding of how robust such predictions are under counterfactual perturbations.
arXiv:2602. 24181v2 Announce Type: replace-cross Abstract: Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks.
arXiv:2606. 08194v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) integrate audio perception and language understanding within a unified framework, enabling a wide range of real-world applications.
arXiv:2606. 08218v1 Announce Type: cross Abstract: Compositional priors describe the generic properties of layered functions in deep Bayesian models, where deep neural networks with random weights are a canonical example.
arXiv:2606. 07635v1 Announce Type: cross Abstract: Multimodal neuroimaging fusion of functional MRI (fMRI) and diffusion tensor imaging (DTI) provides complementary information for cognitive impairment analysis, but remains challenged by heterogeneous feature spaces and misaligned representations.
arXiv:2606. 09092v1 Announce Type: new Abstract: Theory of Mind (ToM) is a must-acquire skill for modern foundation model systems to operate effectively and safely in the real world.
arXiv:2510. 03244v2 Announce Type: replace-cross Abstract: Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores crucial cross-channel dependencies.
arXiv:2606. 09826v1 Announce Type: cross Abstract: Vision-language model (VLM) agents are increasingly deployed in interactive game environments.
Alzheimer's disease (AD) progression is highly heterogeneous and is typically observed through sparse and irregular longitudinal data, posing challenges for prediction and personalised monitoring. Existing machine learning approaches have improved AD prediction using multimodal data, yet often focus on static classification or cohort-level risk estimation, providing limited support for subject-specific modelling and uncertainty-aware reasoning.
3D object detection is the backbone of perception for automated vehicles (AV) and broader intelligent transportation systems applications. Long-range detection is challenging because sensing evidence is sparse; yet this ``long-range'' scenario is routine in traffic.
Crises alter both how people move and how they communicate. During emergencies such as wildfires and pandemics, changes in mobility patterns and online emotional discourse evolve jointly, yet they are typically studied in isolation.
Large language model agents are increasingly deployed in human-human interaction settings, such as meeting assistants and clinical documentation systems, where they must observe conversations and retain information for downstream queries. Unlike traditional human-assistant settings, these environments are inherently multimodal, involve complex discourse phenomena such as anaphora and deixis, and contain asynchronous or conflicting information from multiple participants.
Effective crisis response requires spatially grounded communication that bridges linguistic guidance of civilians with the physical environment, accounting for structural bottlenecks, evolving threats, and agent-specific contexts. Yet, current NLP research in crisis communication remains mainly limited to static, text-only classification settings, overlooking the critical communicative role of AI operators in dynamic, embodied scenarios.
Omni-modal retrieval promises a single embedding space for text, image, video, document, and audio inputs, but building such a unified retriever is difficult since these modalities differ in data distribution, architecture, and optimization dynamics. In this work, we present Conan-embedding-v3, a decouple--fuse--recover framework for omni-modal retrieval.