✨Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

📝 Summary:
daVinci-MagiHuman is an open-source audio-video generative model using a single-stream Transformer for synchronized content from text. It achieves high-quality, human-centric generation with efficient inference and strong evaluation results against leading models.

🔹 Publication Date: Published on Mar 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.21986
• PDF: https://arxiv.org/pdf/2603.21986
• Project Page: https://huggingface.co/spaces/SII-GAIR/daVinci-MagiHuman
• Github: https://github.com/GAIR-NLP/daVinci-MagiHuman

🔹 Models citing this paper:
• https://huggingface.co/GAIR/daVinci-MagiHuman

✨ Spaces citing this paper:
• https://huggingface.co/spaces/SII-GAIR/daVinci-MagiHuman

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#GenerativeAI #AudioVideoAI #FoundationModels #DeepLearning #AIResearch

✨Fair splits flip the leaderboard: CHANRG reveals limited generalization in RNA secondary-structure prediction

📝 Summary:
The CHANRG benchmark reveals RNA foundation models achieve high held-out accuracy but lose significant robustness out-of-distribution. This new benchmark provides a stricter framework for evaluating RNA secondary structure prediction.

🔹 Publication Date: Published on Mar 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22330
• PDF: https://arxiv.org/pdf/2603.22330
• Project Page: https://huggingface.co/datasets/multimolecule/chanrg
• Github: https://github.com/MultiMolecule/multimolecule

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#RNAstructure #MachineLearning #FoundationModels #Bioinformatics #ModelRobustness

✨A Comparative Study in Surgical AI: Datasets, Foundation Models, and Barriers to Med-AGI

📝 Summary:
This paper finds that even state-of-the-art multi-billion parameter AI models struggle with surgical tool detection, a seemingly simple task. Scaling models further offers diminishing returns, suggesting fundamental limitations for current Vision Language Models in surgical use cases beyond just ...

🔹 Publication Date: Published on Mar 28

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.27341
• PDF: https://arxiv.org/pdf/2603.27341

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#SurgicalAI #MedicalAI #FoundationModels #VisionLanguageModels #AIHealthcare

✨ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions

📝 Summary:
ArtHOI presents an optimization-based framework that integrates foundation model priors to reconstruct 4D human-articulated-object interactions from single monocular RGB videos using adaptive sampling...

🔹 Publication Date: Published on Mar 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.25791
• PDF: https://arxiv.org/pdf/2603.25791
• Project Page: https://arthoi-reconstruction.github.io/
• Github: https://github.com/hitcs-zikaiwang/ArtHOI-4D-Reconstruction

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#4DReconstruction #FoundationModels #ComputerVision #HumanObjectInteraction #AI

✨Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

📝 Summary:
Medical imaging datasets are fragmented and small, limiting foundation model development. This survey of 1000+ open-access datasets proposes a metadata-driven fusion paradigm to integrate them, creating larger resources. This scales medical imaging data for more capable foundation models.

🔹 Publication Date: Published on Mar 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.27460
• PDF: https://arxiv.org/pdf/2603.27460
• Project Page: https://huggingface.co/datasets/General-Medical-AI/Project-Imaging-X
• Github: https://github.com/uni-medical/Project-Imaging-X

✨ Datasets citing this paper:
• https://huggingface.co/datasets/General-Medical-AI/Project-Imaging-X

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MedicalImaging #FoundationModels #AI #DataScience #OpenData

✨Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation

📝 Summary:
Omni123 is a 3D-native foundation model unifying text-to-2D and text-to-3D generation. It addresses limited 3D data by leveraging cross-modal consistency from abundant 2D images as a geometric prior. This model significantly improves text-guided 3D generation and editing.

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02289
• PDF: https://arxiv.org/pdf/2604.02289

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#3DGeneration #FoundationModels #AIResearch #ComputerVision #DeepLearning

✨Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains

📝 Summary:
Fine-tuning foundation models causes unpredictable and contradictory changes in safety, invalidating base-model safety evaluations. Safety properties do not persist reliably through adaptation. Explicit re-evaluation of fine-tuned models is crucial to manage risks in high-stakes domains.

🔹 Publication Date: Published on Apr 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.24902
• PDF: https://arxiv.org/pdf/2604.24902

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AISafety #FineTuning #FoundationModels #ResponsibleAI #AIResearch

🔥 Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models

💡 The paper introduces Embodied-R1.5, a unified embodied foundation model that integrates various embodied reasoning capabilities, such as cognition, task planning, correction, and pointing, into a single architecture. The goal is to achieve general physical intelligence. To train the model, the authors developed three automated data construction pipelines, resulting in a large-scale data system of over 15 billion tokens. They also designed a multi-task balanced reinforcement learning approach to alleviate conflicts between different tasks.

The model consists of a Planner-Grounder-Corrector framework, which enables it to autonomously execute and self-correct over long-horizon tasks. With only 8 billion parameters, Embodied-R1.5 achieves state-of-the-art performance on 16 out of 24 embodied vision-language benchmarks, surpassing leading models. The model can also be fine-tuned into a vision-language agent with a small amount of data, outperforming leading models across popular manipulation benchmark suites.

The authors conducted extensive zero-shot real-robot experiments, demonstrating the model's strong generalization to the physical world. The experiments validated the model's performance in instruction following, affordance grounding, articulated object manipulation, and long-horizon complex tasks. The paper's contributions include the introduction of the Embodied-R1.5 model, the development of a large-scale data system, and the creation of an evaluation framework tailored for embodied tasks. The model weights, datasets, training code, and evaluation framework are open-sourced to facilitate future research in embodied foundation models.

The problem addressed in the paper is the development of a unified embodied foundation model that can achieve general physical intelligence. The method used to address this problem is the integration of various embodied reasoning capabilities into a single architecture, along with the development of a large-scale data system and a multi-task balanced reinforcement learning approach. The results show that Embodied-R1.5 achieves state-of-the-art performance on various benchmarks and demonstrates strong generalization to the physical world. Overall, the paper contributes to the development of embodied foundation models and has the potential to facilitate future research in this area.

📅 Published on Jun 9

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.11324
• PDF: https://arxiv.org/pdf/2606.11324
• Project Page: https://embodied-r.github.io/

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#EmbodiedIntelligence #PhysicalReasoning #FoundationModels #CognitiveArchitectures #ArtificialGeneralIntelligence

🔥 GLM-5: from Vibe Coding to Agentic Engineering

💡 The paper introduces GLM-5, a next-generation foundation model that advances the field of coding and software engineering. The current paradigm of vibe coding, which relies on intuitive and often imprecise coding practices, is limited in its ability to handle complex real-world software engineering tasks. To address this, the authors propose GLM-5, which builds upon the agentic, reasoning, and coding capabilities of its predecessor and incorporates several key innovations.

The method used to develop GLM-5 involves the adoption of DSA, which significantly reduces training and inference costs while maintaining long-context fidelity. Additionally, the authors implement a new asynchronous reinforcement learning infrastructure that improves post-training efficiency by decoupling generation from training. Novel asynchronous agent RL algorithms are also proposed to further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively.

The results of the paper demonstrate the effectiveness of GLM-5, which achieves state-of-the-art performance on major open benchmarks. Most notably, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. The model's ability to handle complex coding tasks and its potential to transition the paradigm of vibe coding to agentic engineering make it a significant contribution to the field of data science and software engineering. Overall, the paper presents a major advancement in foundation models and has the potential to impact the way software engineering is practiced.

📅 Published on Feb 17

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2602.15763
• PDF: https://arxiv.org/pdf/2602.15763
• Project Page: https://huggingface.co/spaces/GenAISecurityProject/OWASP-AIBOM-Generator

🤖 Models citing this paper:
• https://huggingface.co/zai-org/GLM-5
• https://huggingface.co/zai-org/GLM-5.1
• https://huggingface.co/zai-org/GLM-5.2

📊 Datasets citing this paper:
• https://huggingface.co/datasets/zai-org/terminal-bench-2-verified
• https://huggingface.co/datasets/harithoppil/terminal-bench-2-verified

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/pliny-the-prompter/obliteratus
• https://huggingface.co/spaces/akhaliq/anycoder
• https://huggingface.co/spaces/GenAISecurityProject/OWASP-AIBOM-Generator

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#AgenticEngineering #FoundationModels #VibeCoding #SoftwareEngineeringInnovations #ReinforcementLearningTechniques

🔥 Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

💡 The paper presents Qwen-RobotManip, a generalizable Vision-Language-Action foundation model for robotic manipulation that achieves strong generalization through unified alignment across representation, motion, and behavior dimensions. The problem addressed is that robotic manipulation data is heterogeneous, expensive to collect, and narrow in diversity, making it challenging to achieve alignment and scale in training. The authors propose a unified alignment framework that enables large-scale multi-source training, allowing the model to absorb manipulation data at a scale that prior training regimes could not sustain.

The method involves a human-to-robot synthesis pipeline that converts egocentric hand demonstrations into robot trajectories across 15 platforms, and a rigorous curation pipeline that harmonizes heterogeneous datasets. The model is trained on a large pretraining corpus of approximately 38,100 hours, constructed using only open-source datasets and human videos without proprietary data collection.

The results show that Qwen-RobotManip exhibits emergent generalization capabilities, including zero-shot instruction following, robustness to perturbations, reactive error recovery, and cross-embodiment transfer. The model substantially outperforms prior state-of-the-art models, including π0.5, across all out-of-distribution settings, and ranks 1st in RoboChallenge with a 20% relative improvement. The model is also validated on real-robot platforms, including AgileX ALOHA, Franka, UR, and ARX. The paper concludes that Qwen-RobotManip achieves genuine generalization in robotic manipulation, demonstrating the effectiveness of the unified alignment framework and large-scale training approach.

📅 Published on Jun 17

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.17846
• PDF: https://arxiv.org/pdf/2606.17846
• Project Page: https://qwen.ai/blog?id=qwen-robotmanip

📊 Datasets citing this paper:
• https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#RobotLearning #FoundationModels #RoboticManipulation #VisionLanguageAction #MultiSourceTraining

🔥 From Foundation to Application: Improving VLA Models in Practice

💡 The paper presents LingBot-VLA 2.0, an improved version of the VLA foundation model, which aims to bridge the gap between laboratory conditions and real-world applications. The main problem addressed is the disparity between the two environments, which hinders the practical implementation of VLA models. To solve this, the authors propose three main improvements.

First, they enhance generalization across tasks and embodiments by expanding the data preprocessing pipeline and training the model on a large dataset of around 60,000 hours of data, including 50,000 hours of robot trajectories from 20 robot configurations and 10,000 hours of human videos.

Second, they extend the action space to include whole-body degrees of freedom, allowing the robots to perform more complex tasks. This is achieved by accommodating degrees of freedom for the heads, waists, mobile bases, and dexterous hands, in addition to dual-arm hardware platforms.

Third, they incorporate predictive dynamics modeling for improved temporal reasoning. This is done by formulating future prediction as a proxy task, using a video representation model for semantic priors and a depth estimation model for geometric cues.

The results show that these modifications have a beneficial impact, as evaluated on the GM-100 benchmark in a generalist setting. Additionally, the expanded pretraining data enables LingBot-VLA 2.0 to demonstrate strong cross-embodiment long-horizon mobile manipulation capability across two robotic platforms. Overall, the paper presents significant improvements to the VLA foundation model, making it more suitable for real-world applications.

📅 Published on Jul 7

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2607.06403
• PDF: https://arxiv.org/pdf/2607.06403
• Project Page: https://technology.robbyant.com/lingbot-vla-v2

📊 Datasets citing this paper:
• https://huggingface.co/datasets/cy0307/awesome-egocentric-atlas

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#VisualLearningAgents #FoundationModels #RobotLearning #EmbodiedAI #VLAmodels

🔥 MonkeyOCRv2: A Visual-Text Foundation Model for Document AI

💡 The paper presents MonkeyOCRv2, a visual-text foundation model for document AI. The problem addressed is that mainstream visual encoders are not effective for document images without document-oriented adaptation, as they are pre-trained on natural images and cannot handle dense text and fine-grained character strokes. To solve this, the authors construct MonkeyDocv2, the largest document-image pre-training corpus, comprising 113 million images spanning 17 languages. They propose a pre-training strategy that jointly learns image-to-text generation and pixel-level document reconstruction, aligning visual representations with textual content and preserving character strokes and layout details.

The authors conduct extensive experiments on five representative document analysis tasks, including text recognition, formular recognition, text detection, document tampering detection, and overlapping text segmentation. Replacing the original encoders with MonkeyOCRv2 consistently improves performance across all five tasks. The model is also validated as the vision encoder of multimodal large language models on more challenging tasks of document parsing and document understanding.

The results show that MonkeyOCRv2 yields a 0.7B document parsing model that sets a new open-source state-of-the-art on the MDPBench benchmark, surpassing the previous best by 2.8% absolute with a vision encoder roughly 11 times smaller. The frozen encoder also powers a document understanding model that outperforms counterparts built on CLIP, DINO, and SAM across eight benchmarks under identical training settings. These results suggest that document-oriented visual pre-training can serve as a foundation for document intelligence in its own right.

📅 Published on Jul 13

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2607.11562
• PDF: https://arxiv.org/pdf/2607.11562

🤖 Models citing this paper:
• https://huggingface.co/zenosai/MonkeyOCRv2-B-Parsing
• https://huggingface.co/zenosai/MonkeyOCRv2-S
• https://huggingface.co/zenosai/MonkeyOCRv2-B

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/zenosai/monkey-ocr-v2

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#DocumentAI #VisualTextModels #FoundationModels #DocumentImageAnalysis #OCRTechnology

🔥 Data Pyramid for Embodied Manipulation

💡 The paper proposes a data pyramid framework for embodied manipulation, which organizes data sources into five complementary categories: real-robot data, UMl-style data, egocentric and exocentric data, simulation data, and general vision-language data. The framework is designed to address the challenges of embodied agents, which require data that couples observations with physical states and actions. The authors analyze recent embodied foundation models through the lens of their data recipes, examining how different sources are selected, aligned, and mixed during training. They relate data composition to capabilities in perception, reasoning, planning, action generation, and world prediction. The paper also discusses six open challenges, including building large-scale tactile datasets, collecting failure and recovery data, developing scalable data-collection pipelines, aligning actions across embodiments, leveraging egocentric data for dexterous manipulation, and designing principled data recipes for robot learning. The proposed data pyramid framework provides a foundation for the design of next-generation embodied systems, which can learn to perceive, reason, and act in complex environments. The authors hope that this work will pave the way for the development of more advanced embodied agents that can learn from diverse data sources and improve their performance in various tasks.

📅 Published on Jul 27

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2607.24744
• PDF: https://arxiv.org/pdf/2607.24744
• Project Page: https://jasper-aaa.github.io/embodied-data-pyramid/

━━━━━━━━━━━━━━━━━━━━━━━━
📢 By: https://xn--r1a.website/PaperNexus

#EmbodiedManipulation #RobotLearning #MultimodalData #EmbodiedAI #FoundationModels