Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal blindness, the inability to perceive fundamental cues like order, direction, and motion dynamics. Stand...
Graphic designers often blend visual concepts to communicate multiple ideas within a single image, leveraging positive and negative space to create balance, emphasis, and aesthetic appeal. While compu...
We present Qwen-Drive-1.0, an initial step towards a vision-language foundation model for autonomous driving. Qwen-Drive-1.0 retains the architecture of the pretrained vision-language model (VLM) and...
Vision-Language Models (VLMs) still struggle on tasks requiring complex visual understanding. We argue that the core issue is not high-level reasoning, but instead failing to locate critical details i...
Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract, integrate, and interpret biomedical knowledge relevant to cancer genomics, yet their translation in...
Performance evaluation for surface-water segmentation commonly uses an aggregate metric such as global intersection-over-union (IoU) to rank model configurations. However, a configuration ranking does...
Multimodal models often build on architectures designed for generative vision-language modeling, typically combining separately pretrained vision encoders with causal language models. Visual document...
Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity cannot be assumed. Prior work on repository poisoning...
Multimodal Large Language Models (MLLMs) are increasingly deployed in multi-image scenarios requiring complex reasoning across visual contexts. However, current MLLMs remain fundamentally limited by o...
Multimodal Large Language Models (MLLMs) have shown remarkable success in STEM domains, where progress is often driven by vertical, step-by-step deduction under relatively stable symbol systems. Their...
We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation. It includes two tasks: (i) AynVQA, covering spoken visual question answering and image-gro...
Antimicrobial peptides (AMPs) often act against multiple pathogen classes, making multi-label activity prediction a more realistic screening target than binary antimicrobial classification. The ESCAPE...
Indirect speech acts (ISAs) require pragmatic reasoning over context, as directive intent can- not be inferred from surface form alone. Prior text-based studies and existing multimodal benchmarks larg...
Generalized Visual Grounding (GVG) task aims to localize targets in an image based on referring expressions, extends the classical visual grounding paradigm by integrating multi-target and non-target...
arXiv:2510.17198v2 Announce Type: replace Abstract: Riverbank erosion is a serious environmental problem in Bangladesh, causing land loss, damage to infrastructure, and displacement of local communit...
The paper introduces GMA, a new benchmark for evaluating general mobile assistants in realistic, challenging scenarios. GMA expands on existing benchmarks by offering seven open‑source applications across diverse domains and 300 tasks organized into four difficulty tiers, ranging from simple actions to complex multi‑step workflows. The authors evaluate eight state‑of‑the‑art models, showing that performance drops sharply with task complexity, and conduct ablation studies on harness design—such as context retention and state tracking—to demonstrate how these choices can improve outcomes, especially for demanding workflows.
The paper introduces a Mixture of Multicenter Experts (MoME) framework that leverages diverse clinical strategies to reduce bias in medical AI without sharing data across institutions. MoME integrates specialized expertise from multiple centers, improving generalizability and adaptability of a multimodal target volume delineation model for prostate cancer radiotherapy. The model, trained with few-shot imaging and clinical notes, outperformed baselines, especially in high inter‑center variability or limited data scenarios, and allows local customization without cross‑institutional data exchange.
arXiv:2509.24192v2 Announce Type: replace Abstract: Vision-language models (VLMs) have advanced multimodal perception, demonstrated by open-vocabulary object detection with simple language queries. S...
The paper investigates how to evaluate audio‑language models by separating the use of acoustic evidence from the need to invoke a generative audio model. Using a controlled call‑decision framework, the authors compare policies that rely on transcript labels, encoder outputs from CLAP, AST, or WavLM, and optional calls to generative models such as Qwen2‑Audio, Qwen2.5‑Omni, or MOSS‑Audio. Results on the VocalSound dataset show that while transcript‑only accuracy is low (0.296), encoder‑only controls achieve high accuracy (≈0.85) without any generative calls, and adding generative calls yields only a marginal improvement (0.925 vs. 0.921).
Ada-TokenCom is a rate‑adaptive token communication framework that uses large autoregressive models to compress and transmit tokens efficiently. It combines next‑token prediction with arithmetic coding, sending only the most informative tokens and letting the receiver generate the rest. A Lyapunov‑based algorithm dynamically adjusts compression and modulation to match changing network conditions, and simulations show it outperforms existing digital and deep joint source‑channel coding baselines.