Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2607. 27665v1 Announce Type: new Abstract: Federated graph learning enables collaborative training over decentralized graph data without sharing raw graph information.
arXiv:2605. 17480v3 Announce Type: replace Abstract: Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces.
arXiv:2601. 11178v3 Announce Type: replace Abstract: Social media platforms are increasingly dominated by long-form multimodal content, where harmful narratives are constructed through a complex interplay of audio, visual, and textual cues.
arXiv:2512. 00807v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) inherit significant social biases from their training data, notably in gender representation.
arXiv:2607. 27084v1 Announce Type: cross Abstract: Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in scientific papers.
arXiv:2607. 27066v1 Announce Type: cross Abstract: Scientific figure assessment in peer review differs fundamentally from general image quality evaluation: a figure must be visually legible, faithfully support the manuscript's claims, and communicate evidence with a clear visual hierarchy.
arXiv:2607. 26947v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) rely on a projector to align visual representations with the language embedding space, making it central to cross-modal understanding.
arXiv:2607. 26769v1 Announce Type: cross Abstract: Multimodal large language models increasingly use sketches, annotations, tools, and intermediate images during reasoning, but it remains unclear whether they truly rely on these visual states.
arXiv:2607. 26410v1 Announce Type: cross Abstract: We present Voice Memory, a inference-only scheme for agentic speech recognition: at stream time, a frozen corrector reads a single per-domain memory.
arXiv:2607. 28374v1 Announce Type: new Abstract: Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy.
arXiv:2607. 27549v1 Announce Type: cross Abstract: Recent progress in large-scale imitation learning for robot manipulation has been driven by leveraging datasets across a wide range of robot embodiments.
arXiv:2607. 26698v1 Announce Type: cross Abstract: Cover song generation (CSG) should preserve the melodic and linguistic content of a reference song while recreating the remaining musical components.
arXiv:2607. 27766v1 Announce Type: cross Abstract: On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference.
Effective flood monitoring is critical for minimizing the impacts of flood disasters on populations and infrastructure. Yet reliable remote sensing across extensive and environmentally diverse regions remains challenging, as most segmentation algorithms lack the generalisation capacity required for large-scale application, while annotated flood data are scarce and unevenly distributed.
Computer-use agents often fail on transient GUI events because they produce the correct action only after the relevant window has already closed. We identify the main cause as expensive autoregressive decoding on the decision-time critical path.
Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy. This aggregate signal cannot tell whether a correct answer was reached through grounded evidence, language priors, or accidental error cancellation.
Vision-Language Models (VLMs) such as CLIP are now foundational to multimodal systems, yet their robustness to spurious correlations remains poorly understood at scale. We present the first large-scale empirical study of 194 publicly available VLMs, including 16 model families, covering a wide range of model sizes, 24 training datasets, and three evaluation benchmarks, namely ImageNet (overall performance), CelebA (typical single-attribute bias), and UrbanCars (complex multi-attribute biases).
Credit assignment is a fundamental challenge in cooperative multi-agent reinforcement learning, particularly in embodied AI settings characterized by limited and delayed feedback as well as dynamically changing numbers of active agents. We propose MARS-RA, a framework that reformulates credit assignment as a rank aggregation problem using contribution-based pairwise comparisons among agents generated by large multimodal models.
Due to their strong generalizable multimodal processing and reasoning capabilities, Multimodal Large Language Models (MLLMs) have demonstrated significant potential as universal image retrievers, effectively addressing diverse real-world image retrieval tasks. Nevertheless, pioneering studies, while promising, overlook the potential of fine-grained context modeling and disentangled fine-tuning objectives in enhancing MLLMs' retrieval performance, particularly for complex tasks such as long-text-to-image retrieval, visual dialog retrieval, and composed image retrieval (CIR).
Multimodal foundation models are reshaping edge-cloud visual intelligence from task-specific feature pipelines into token-based interfaces, where edge devices encode visual inputs into tokens for a general-purpose cloud MLLM. However, dense visual-token sequences increase cloud-side inference costs.