The paper introduces a real‑time framework for generating co‑speech gestures for digital humans, coupling a streaming speech response module with a causal multimodal autoregressive gesture generator that uses only current speech and motion history. It also presents an offline data synthesis pipeline for virtual companion dialogues and a self‑evolving training loop that incorporates user feedback to continually adapt the model. Experiments show the system achieves a better latency‑quality trade‑off, stronger speech‑motion synchronization, and higher user preference than existing baselines.
By Wentao Jiang, Youchen Xie, Haidi Fan, Yajing Chen, Xin Wang, Ye Shi, Jingya Wang
RefLAM is a pipeline that converts manuscript page images and clean transcriptions into validated, line-level ground truth for Arabic handwritten text recognition. It combines a deep‑learning page‑segmentation model, a multimodal large language model for structured OCR, and a diacritic‑agnostic fuzzy alignment engine that assigns a confidence score to each line, with a provable correctness guarantee for perfect scores. Using RefLAM, the authors achieved a 75× speedup over manual annotation and released AraMS‑28k, a dataset of 14 historical Arabic manuscripts with detailed annotations.
By Mohamed Guechaoui, Mohamed Diaa Zellagui, Souleyman Chaib, Sahraoui Dhelim
CardioFusion-AI is a framework for robust fusion of ECG and PPG signals in wearable physiological monitoring. Its signal‑processing front end, featuring R‑peak and systolic‑peak detection, an Orphanidou‑type signal‑quality index, and beat‑by‑beat pulse transit time estimation, was validated on 53 intensive‑care recordings and a fetal ECG database. In a controlled synthetic degradation study, attention fusion achieved the lowest overall error, while adaptive gates reallocated weight toward the healthy modality under complete loss, and signal‑quality conditioning improved performance when PPG was missing.
By Navaneetha Krishnan Kamalakannan, Janakiraman Kamalakannan
The paper introduces the Hybrid Hierarchical Multi-Agent Framework (H$^{2}$MAF), which fuses decision-level outputs from EfficientNet-B3 and ConvNeXt-Tiny with semantic arbitration by multimodal large language models Gemma 4 E4B and Qwen3.5 4B to produce explainable plant disease diagnoses. Evaluated on 14,364 images from PlantDoc and two Cornell robotic field datasets, the framework achieves up to 99.3% accuracy, with Gemma improving PlantDoc accuracy from 63.9% to 68.5% and demonstrating low critical‑risk error. The results highlight the potential of MLLM arbitration for reliable, explainable agricultural AI under real‑world field conditions.
By Ranjan Sapkota, Konstantinos I. Roumeliotis, Pengyao Xie, Nikolaos D. Tselikas, Lirong Xiang, Manoj Karkee
ARGenSeg introduces an autoregressive generation-based approach for image segmentation that integrates seamlessly with multimodal large language models (MLLMs). Unlike prior methods that use boundary points or dedicated segmentation heads, ARGenSeg generates dense masks directly through visual token output and detokenization via a universal VQ‑VAE, enabling fine‑grained pixel‑level perception. The framework employs a next‑scale‑prediction strategy to parallelize token generation, resulting in faster inference while outperforming state‑of‑the‑art segmentation models on multiple datasets.
By Xiaolong Wang, Lixiang Ru, Ziyuan Huang, Kaixiang Ji, Dandan Zheng, Jingdong Chen, Jun Zhou
PreResQ‑R1 introduces a Preference‑Response Disentangled Reinforcement Learning framework for Visual Quality Assessment that jointly optimizes absolute score regression and relative ranking consistency. It employs a dual‑branch reward system—modeling intra‑sample response coherence and inter‑sample preference alignment—trained with Group Relative Policy Optimization. The method extends to video quality assessment via a global‑temporal and local‑spatial data flow strategy, achieving state‑of‑the‑art results on 10 IQA and 5 VQA benchmarks with only 6K images and 28K videos, and provides human‑aligned reasoning traces.
By Zehui Feng, Weichuan Wang, Xiaohan Chen, Ting Han
OVO‑S‑Bench is a fully human‑annotated benchmark designed to evaluate streaming spatial intelligence in multimodal large language models (MLLMs). It contains 1,680 questions derived from 348 source videos, each with a query timestamp and evidence interval, and tests models on four levels of abstraction: instantaneous egocentric perception, spatiotemporal context tracking, generative spatial reasoning, and allocentric spatial mapping. Across 38 MLLMs, Gemini‑3.1‑Pro scored 59.2 versus 92.2 for human experts, with allocentric spatial mapping identified as the main challenge, and the benchmark reveals that chain‑of‑thought reasoning can worsen spatial errors when not grounded in the stream.
By Yifei Li, Pengyiang Liu, Yuhang Zang, Zhongyue Shi, Qi Fu, Hongye Hao, Jiwen Lu
The paper presents a training‑free, agentic computer‑vision system that converts 2D structural framing plan PDFs into editable finite‑element model drafts. It uses a deterministic stage to extract geometric primitives, estimate scale, and recognize five entity classes via a drafting grammar, followed by an agentic stage that applies typed corrections and fail‑closed transactions. Evaluation on a 100‑plan benchmark shows high precision and recall across columns, beams, walls, braces, and openings, with scale estimates within 0.1% of reference.
By Mohammad Talebi-Kalaleh, Qipei Mei
VBVR-Pro is a closed‑loop testbed that enables native visual reasoning through generation, offering 300 procedurally generated tasks that scale training and allow strong transfer to external benchmarks. It supplies verifiable reward scorers based on deterministic, task‑specific rules, outperforming VLM‑as‑a‑judge approaches and providing reliable signals for reinforcement learning. The suite also facilitates controlled modality studies, revealing that video generation excels at persistent spatiotemporal tracking while interleaved generation offers a compute‑efficient alternative, and highlights the importance of vision‑native trajectories for reasoning.
By Junxiang Xu, Ruisi Wang, Fanyi Pu, Maijunxian Wang, Ran Ji, Tongxi Zhou, Chenyang Gu, Jing Zuo, Hongcan Xiao, Yimeng Geng, Wanqi Yin, Wei Chen, Oscar Qian, Zhengan Yan, Ziqi Huang, Haiwen Diao, Liang Pan, Bo Li, Xiangyu Fan, Dezhi Luo, Fengyuan Yu, Zehong Zhao, Qingying Gao, Tinghui Zhu, Yilan Zhang, Jingqi Tong, Pinyuan Feng, Zhengze Jiang, Letian Wang, Ziyu Guo, Renrui Zhang, Jieneng Chen, Sonia Joseph, Constantin Venhoff, Saman Motamed, Mengyue Yang, Chandra Sripada, Alan Yuille, Philip Torr, Lvmin Zhang, Vikash Kumar, Daniel Khashabi, Nikolaus Kriegeskorte, Rapha\"el Milli\`ere, Vincent C. M\"uller, Anyi Rao, Quan Wang, Ziwei Liu, Dahua Lin, Lei Yang, Hokin Deng, Zhongang Cai
Qwen3.8-Flash-Next is an open‑weights multimodal Mixture‑of‑Experts (MoE) model previewing the architecture of Qwen4. It contains 125 B tokens with only 6 B active, giving a performance boost. The author has tested it on a DGX Spark with Unsloth quantized models, exploring variants like UD‑IQ1_S and UD‑Q2_K_XL, and highlighted a high‑reasoning‑effort example from UD‑Q2_K_XL.
In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed MLLMs to continually evolve from streaming unlabeled data. Existing unsupervised p...
Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as pi0.5 operate under a single-frame paradigm, limiting their ability to re...
Reasoning in language allows foundation models to spend more test-time compute on hard problems, such as those requiring decomposition, constraint tracking, and prediction of future consequences. Whet...
Wearable electrocardiogram (ECG) and photoplethysmogram (PPG) sensors are complementary but individually fragile: motion artifact, poor contact, and sensor dropout can degrade one or both signals. Fus...
Subgroup performance differences are the standard evidence for fairness bias in medical imaging, and the usual response removes the demographic information that a model encodes. Here we introduce Fair...
Traffic Anomaly Understanding (TAU) requires models and systems to detect, reason about, and explain anomalous events in transportation videos. To address this challenge, we propose TAU-Agent, an agen...
Understanding user preferences from noisy and temporally evolving social media behaviors is fundamentally challenging due to interest drift, where user preferences shift across time and exhibit both m...
Safety evaluation is critical for assessing whether aligned Large Language Models (LLMs) remain robust against jailbreak attacks. Existing automated testing methods, however, largely rely on response-...
In 2026, we held the fourth iteration of the SHROOM Shared Task series: SHROOM-Visions (\textbf{S}hared-task on \textbf{H}allucinations and \textbf{R}elated \textbf{O}bservable \textbf{O}vergeneration...
Pretrained vision-language models such as CLIP excel at zero-shot recognition but often fail at compositionality, particularly attribute-object and relational structures. Recent studies mitigate this...