Across four multimodal LLM backbones, MRPO consistently outperforms standard GRPO and a recent RL baseline, and on Qwen3-VL-8B-Thinking even surpasses substantially larger medical MLLMs such as HuatuoGPT-Vision-34B by 4.59 points.
Across six real-world scenarios, human raters prefer JoyAI-VL-Interaction over the in-app video-call assistants of Doubao and Gemini by a wide margin, and the first open, vision-driven interaction model released together with its training recipe, data, and complete deployable system.
Ding-Yu Yao, Jun Zhou, Chenxu Yang et al.· arXiv.org· 10 citations
Hungarian matching with filtering and Repulsion Loss are introduced to enforce more uniform vertex distribution across the reconstructed model, and the vertex clustering issue observed in the prior work is substantially alleviated.
A software-based approach that reconstructs a 3D oral model using only ten 2D intraoral images captured from different angles, requiring no dedicated hardware devices is proposed, which reduces cost, eliminates the need for physical scanning equipment, minimises patient discomfort, and enables automated 3D reconstructi...
Preliminary results indicate that a world-action model (WAM) post-trained from OmniDreams achieves strong performance on the Physical AI Autonomous Vehicles NuRec dataset, surpassing the VLA-based Alpamayo 1.5 research policy model while using only 1/5 the total parameters.
This work introduces a 3D foundation model for LSM data, pretrained on a large curated collection of 3D images spanning multiple organisms, stains, and imaging protocols, and learns transferable volumetric representations by jointly optimizing for masked reconstruction and image-text alignment.
Adina Scheinfeld, Hao-Tan Zhang, Shang Mu et al.· arXiv.org· 1 citation
Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator results shape the next population but are not preserved as reusable design knowledge. We present Auto-Robotist, a self-evolving LLM agent that distills morphology-search t...
Yunfei Wang, Xiaohao Xu, Yang Li et al.· 0 citations
This work constructs a specialized dataset to demystify the emotional circuits underlying the three-stage ``Adapt-Aggregate-Execute''mechanism and discovers a functional decoupling: visual emotional cues are aggregated in middle layers via sentiment-specific attention heads, but are subsequently translated into narrati...
MPFlow is proposed, a zero-shot multi-modal reconstruction framework built on rectified flow that incorporates auxiliary MRI modalities at inference time without retraining the generative prior to improve anatomical fidelity.
Seung-Sik Kim, Chen Jin, H. Tregidgo et al.· arXiv.org· 0 citations
This study systematically dissects design choices along three dimensions: foundational components, perception essentials, and action modeling perspectives and distill 12 key findings that together form a practical recipe for building strong VLA models, resulting in a simple yet effective model, VLANeXt.
Xiao-Ming Wu, Kang Liao, Yi-Hang Luo et al.· 12 citations· ⚡3
A lightweight Cross-Layer Fusion Adapter (CLFA) framework that repurposes Contrastive Language--Image Pre-training for handwriting-based AD screening and progressively aligns pretrained vision--language representations with AD-related handwriting cues and supports transfer from supervised source tasks to task-disjoint...
Chang-Qing Gong, Hua-Feng Qin, Mounîm A. El-Yacoubi· 0 citations
The Band-Attention Modulation Network (BAM-Net) is proposed, a novel framework that pioneers learnable, fine-grained modulation of frequency components for forgery detection and exhibits exceptional generalization in cross-dataset, cross-compression, and cross-manipulation scenarios.
Zhi-Da Zhang, Wen-Kui Yang, Xin Ma et al.· 1 citation
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
