⚡️Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds
HF: https://huggingface.co/papers/2511.08892
Peoject: https://www.lumine-ai.org/
Paper: https://arxiv.org/abs/2511.08892
@Machine_learn
HF: https://huggingface.co/papers/2511.08892
Peoject: https://www.lumine-ai.org/
Paper: https://arxiv.org/abs/2511.08892
@Machine_learn
huggingface.co
Paper page - Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds
Join the discussion on this paper page
❤1👍1
Forwarded from Papers
Title: A Multi-Task Framework Unifying Classification and Regression for Microgrid Power (kWh) Forecasting: Modified FEDformer
Abstract:........
Keywords: Microgrid Power forecasting; Transformer; FedFormer; Regression; Classification
Price:
2: 500$
3: 400$
Journal: IEEE Power & Energy Society
@Raminmousa
@Paper4money
@Machine_learn
Abstract:........
Keywords: Microgrid Power forecasting; Transformer; FedFormer; Regression; Classification
Price:
2: 500$
3: 400$
Journal: IEEE Power & Energy Society
@Raminmousa
@Paper4money
@Machine_learn
❤3
🔥 Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild
💡 The paper presents Lift4D, a test-time optimization framework for reconstructing dynamic non-rigid objects from monocular video. The problem addressed is the difficulty in reconstructing 4D representations of dynamic objects from single-view video due to the scarcity of 4D training data and the limitations of prior approaches that either directly predict 4D representations or initialize a 3D representation and refine it based on video evidence.
The method involves adapting a single-view 3D reconstruction model to yield temporally consistent per-frame predictions, which provides a coherent initialization for a deformable 3D Gaussian Splatting representation. This representation is then optimized to match the input video through an occlusion-aware optimization that recovers visible surface details and completes unobserved regions using a view-conditioned diffusion prior.
The results show that Lift4D improves over prior 4D reconstruction methods, particularly on challenging in-the-wild sequences with severe occlusions and non-rigid motion. The framework effectively handles complex scenarios by integrating visual cues from direct observations with data-driven priors over geometry and appearance, making it a significant contribution to the field of 4D reconstruction from monocular video.
📅 Published on Jun 22
🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.23688
• PDF: https://arxiv.org/pdf/2606.23688
• Project Page: https://lift4d.github.io/
━━━━━━━━━━━━━━━━━━━━━━━━
@Machine_learn
💡 The paper presents Lift4D, a test-time optimization framework for reconstructing dynamic non-rigid objects from monocular video. The problem addressed is the difficulty in reconstructing 4D representations of dynamic objects from single-view video due to the scarcity of 4D training data and the limitations of prior approaches that either directly predict 4D representations or initialize a 3D representation and refine it based on video evidence.
The method involves adapting a single-view 3D reconstruction model to yield temporally consistent per-frame predictions, which provides a coherent initialization for a deformable 3D Gaussian Splatting representation. This representation is then optimized to match the input video through an occlusion-aware optimization that recovers visible surface details and completes unobserved regions using a view-conditioned diffusion prior.
The results show that Lift4D improves over prior 4D reconstruction methods, particularly on challenging in-the-wild sequences with severe occlusions and non-rigid motion. The framework effectively handles complex scenarios by integrating visual cues from direct observations with data-driven priors over geometry and appearance, making it a significant contribution to the field of 4D reconstruction from monocular video.
📅 Published on Jun 22
🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.23688
• PDF: https://arxiv.org/pdf/2606.23688
• Project Page: https://lift4d.github.io/
━━━━━━━━━━━━━━━━━━━━━━━━
@Machine_learn
GitHub
Hugging Face
The AI community building the future. Hugging Face has 443 repositories available. Follow their code on GitHub.
❤1
Forwarded from Github LLMs
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
https://arxiv.org/abs/2602.24286
@LLM_learning
https://arxiv.org/abs/2602.24286
@LLM_learning
arXiv.org
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA...
GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large...
Papers
Title: A Multi-Task Framework Unifying Classification and Regression for Microgrid Power (kWh) Forecasting: Modified FEDformer Abstract:........ Keywords: Microgrid Power forecasting; Transformer; FedFormer; Regression; Classification Price: 2: 500$ 3:…
سلام دوستانی که مقاله ی Transaction می خواستن می تونن در این مقاله مشارکت کنند.
@Raminmousa
@Raminmousa
Dataset Name: LFW - People (Face Recognition)
Basic Description: The Labeled Faces in the Wild face recognition dataset.
📖 FULL DATASET DESCRIPTION:
==================================
Welcome to Labeled Faces in the Wild, a database of face photographs designed for studying the problem of unconstrained face recognition. The data set contains more than 13,000 images of faces collected from the web. Each face has been labeled with the name of the person pictured. 1680 of the people pictured have two or more distinct photos in the data set. The only constraint on these faces is that they were detected by the Viola-Jones face detector.
📥 DATASET DOWNLOAD INFORMATION
==================================
🔴 Dataset Size: Download dataset as zip (244 MB)
🔰 Direct dataset download link:
https://www.kaggle.com/api/v1/datasets/download/atulanandjha/lfwpeople
📊 Additional information:
==================================
File count not found
Views: 268,000
Downloads: 47,300
@Machine_learn
Basic Description: The Labeled Faces in the Wild face recognition dataset.
📖 FULL DATASET DESCRIPTION:
==================================
Welcome to Labeled Faces in the Wild, a database of face photographs designed for studying the problem of unconstrained face recognition. The data set contains more than 13,000 images of faces collected from the web. Each face has been labeled with the name of the person pictured. 1680 of the people pictured have two or more distinct photos in the data set. The only constraint on these faces is that they were detected by the Viola-Jones face detector.
📥 DATASET DOWNLOAD INFORMATION
==================================
🔴 Dataset Size: Download dataset as zip (244 MB)
🔰 Direct dataset download link:
https://www.kaggle.com/api/v1/datasets/download/atulanandjha/lfwpeople
📊 Additional information:
==================================
File count not found
Views: 268,000
Downloads: 47,300
@Machine_learn
❤6
BOOM! I Got a 4x AI Speed Improvement!
NEw Paper: AutoMem Turns Memory Management into a Trainable Cognitive Skill, Boosting Long-Horizon Agents 2-4x
arxiv.org/abs/2607.01224
@Machine_learn
NEw Paper: AutoMem Turns Memory Management into a Trainable Cognitive Skill, Boosting Long-Horizon Agents 2-4x
arxiv.org/abs/2607.01224
@Machine_learn
❤3
Dataset Name: Real / Fake Job Posting Prediction
Basic Description: Dataset of real and fake job postings
📖 FULL DATASET DESCRIPTION:
==================================
This dataset contains 18K job descriptions out of which about 800 are fake. The data consists of both textual information and meta-information about the jobs. The dataset can be used to create classification models which can learn the job descriptions which are fraudulent.
The University of the Aegean | Laboratory of Information & Communication Systems Security http://emscad.samos.aegean.gr/
The dataset is very valuable as it can be used to answer the following questions:
📥 DATASET DOWNLOAD INFORMATION
==================================
🔴 Dataset Size: Download dataset as zip (17 MB)
🔰 Direct dataset download link:
https://www.kaggle.com/api/v1/datasets/download/shivamb/real-or-fake-fake-jobposting-prediction
📊 Additional information:
==================================
File count not found
Views: 341,000
Downloads: 41,400
@Machine_learn
Basic Description: Dataset of real and fake job postings
📖 FULL DATASET DESCRIPTION:
==================================
This dataset contains 18K job descriptions out of which about 800 are fake. The data consists of both textual information and meta-information about the jobs. The dataset can be used to create classification models which can learn the job descriptions which are fraudulent.
The University of the Aegean | Laboratory of Information & Communication Systems Security http://emscad.samos.aegean.gr/
The dataset is very valuable as it can be used to answer the following questions:
📥 DATASET DOWNLOAD INFORMATION
==================================
🔴 Dataset Size: Download dataset as zip (17 MB)
🔰 Direct dataset download link:
https://www.kaggle.com/api/v1/datasets/download/shivamb/real-or-fake-fake-jobposting-prediction
📊 Additional information:
==================================
File count not found
Views: 341,000
Downloads: 41,400
@Machine_learn
❤1
🔥 MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management
💡 The paper introduces MemGUI-Agent, a mobile GUI agent designed to address the limitations of existing agents on long-horizon tasks. Current agents struggle with retaining intermediate facts across many steps and app transitions, leading to unreliable performance. This limitation is attributed to the ReAct-style prompting approach, which passively accumulates per-step records, causing prompt explosion and dilution of critical cross-app facts.
To address this issue, the authors propose MemGUI-Agent, which uses proactive context management through Context-as-Action, or ConAct. ConAct casts context management as first-class actions emitted by the same policy that selects UI actions. This approach maintains three structured context fields: folded action history, folded UI state, and recent step record, preserving critical UI facts while keeping context compact.
The authors also introduce MemGUI-3K, a dataset with 2,956 trajectories and full ConAct annotations for supervised training and offline analysis. Training an 8B model on MemGUI-3K results in MemGUI-8B-SFT, an 8B MemGUI-Agent that achieves the best open-data 8B performance on MemGUI-Bench and generalizes to the out-of-distribution MobileWorld benchmark.
The contributions of the paper are threefold. Firstly, it identifies the limitations of existing mobile GUI agents on long-horizon tasks and attributes them to the ReAct-style prompting approach. Secondly, it proposes MemGUI-Agent with proactive context management through ConAct, which addresses the limitations of existing agents. Finally, it introduces MemGUI-3K, a dataset for supervised training and offline analysis, and demonstrates the effectiveness of MemGUI-8B-SFT, an 8B MemGUI-Agent trained on this dataset. The code, data, and trained models will be released to facilitate further research and development.
📅 Published on Jun 18
🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.19926
• PDF: https://arxiv.org/pdf/2606.19926
• Project Page: https://memgui-agent.github.io/
🤖 Models citing this paper:
• https://huggingface.co/lgy0404/MemGUI-8B-SFT
📊 Datasets citing this paper:
• https://huggingface.co/datasets/lgy0404/MemGUI-3K
━━━━━━━━━━━━━━━━━━━━━━━━
@Machine_learn
💡 The paper introduces MemGUI-Agent, a mobile GUI agent designed to address the limitations of existing agents on long-horizon tasks. Current agents struggle with retaining intermediate facts across many steps and app transitions, leading to unreliable performance. This limitation is attributed to the ReAct-style prompting approach, which passively accumulates per-step records, causing prompt explosion and dilution of critical cross-app facts.
To address this issue, the authors propose MemGUI-Agent, which uses proactive context management through Context-as-Action, or ConAct. ConAct casts context management as first-class actions emitted by the same policy that selects UI actions. This approach maintains three structured context fields: folded action history, folded UI state, and recent step record, preserving critical UI facts while keeping context compact.
The authors also introduce MemGUI-3K, a dataset with 2,956 trajectories and full ConAct annotations for supervised training and offline analysis. Training an 8B model on MemGUI-3K results in MemGUI-8B-SFT, an 8B MemGUI-Agent that achieves the best open-data 8B performance on MemGUI-Bench and generalizes to the out-of-distribution MobileWorld benchmark.
The contributions of the paper are threefold. Firstly, it identifies the limitations of existing mobile GUI agents on long-horizon tasks and attributes them to the ReAct-style prompting approach. Secondly, it proposes MemGUI-Agent with proactive context management through ConAct, which addresses the limitations of existing agents. Finally, it introduces MemGUI-3K, a dataset for supervised training and offline analysis, and demonstrates the effectiveness of MemGUI-8B-SFT, an 8B MemGUI-Agent trained on this dataset. The code, data, and trained models will be released to facilitate further research and development.
📅 Published on Jun 18
🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.19926
• PDF: https://arxiv.org/pdf/2606.19926
• Project Page: https://memgui-agent.github.io/
🤖 Models citing this paper:
• https://huggingface.co/lgy0404/MemGUI-8B-SFT
📊 Datasets citing this paper:
• https://huggingface.co/datasets/lgy0404/MemGUI-3K
━━━━━━━━━━━━━━━━━━━━━━━━
@Machine_learn
GitHub
Hugging Face
The AI community building the future. Hugging Face has 443 repositories available. Follow their code on GitHub.
❤1