🔥 The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning

💡 The paper introduces a large scale dataset collection called The Well which provides diverse numerical simulations for machine learning models in physical systems simulation. The problem addressed is that standard datasets in this space often cover small classes of physical behavior making it difficult to evaluate the efficacy of new approaches. To address this gap the authors created The Well which is a collection of datasets containing numerical simulations of a wide variety of spatiotemporal physical systems. The dataset draws from domain experts and numerical software developers and provides 15 terabytes of data across 16 datasets covering diverse domains such as biological systems fluid dynamics acoustic scattering and magneto hydrodynamic simulations. The authors also provide a unified PyTorch interface for training and evaluating models to facilitate usage of The Well. The dataset and code are available for use and the authors demonstrate the function of the library by introducing example baselines that highlight the new challenges posed by the complex dynamics of The Well. The main contribution of the paper is the creation of a large scale diverse dataset that can be used to benchmark machine learning models in physical systems simulation and provide a more comprehensive evaluation of their efficacy.

📅 Published on Nov 30, 2024

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2412.00568
• PDF: https://arxiv.org/pdf/2412.00568

📊 Datasets citing this paper:
• https://huggingface.co/datasets/polymathic-ai/acoustic_scattering_inclusions
• https://huggingface.co/datasets/polymathic-ai/rayleigh_benard
• https://huggingface.co/datasets/polymathic-ai/planetswe

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/polymathic-ai/TheWell

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

#PhysicsSimulations #MachineLearningModels #PhysicalSystemsSimulation #NumericalSimulations #SpatiotemporalData

🔥 olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models

💡 The paper presents olmOCR, an open source toolkit that uses a fine tuned vision language model to extract clean text from PDF documents while preserving their structure. The problem addressed is that PDFs come in diverse formats and visual layouts, making it challenging to extract and represent their content for language model use. The method involves using a 7 billion parameter vision language model trained on a sample of 260,000 pages from over 100,000 crawled PDFs with diverse properties. The model is fine tuned to process PDFs into clean linearized plain text in natural reading order, preserving structured content such as sections, tables, lists, and equations. The results show that olmOCR is optimized for large scale batch processing, able to scale flexibly to different hardware setups, and can convert a million PDF pages for a relatively low cost of 190 USD. The toolkit is released as open source, including the vision language model weights, data, training code, and inference code, making it accessible for use in training language models with the trillions of tokens available in PDF documents. Overall, the paper contributes a scalable and cost effective solution for unlocking the content of PDF documents, which can be used to train high quality language models.

📅 Published on Feb 25, 2025

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2502.18443
• PDF: https://arxiv.org/pdf/2502.18443
• Project Page: https://olmocr.allenai.org/

📊 Datasets citing this paper:
• https://huggingface.co/datasets/allenai/olmOCR-bench
• https://huggingface.co/datasets/shhdwi/olmocr-pre-rendered
• https://huggingface.co/datasets/Voxel51/olmOCR_bench

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/davanstrien/benchmark-race
• https://huggingface.co/spaces/OpenEvals/every-leaderboards
• https://huggingface.co/spaces/OpenEvals/leaderboard-watcher

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

#VisionLanguageModels #PDFTextExtraction #DocumentLayoutAnalysis #OCRTechniques #NaturalLanguageProcessing

🔥 Training Video Foundation Models with NVIDIA NeMo

💡 The paper addresses the challenges of training large scale high quality video foundation models that can generate high quality videos. Video foundation models have been used to simulate the real world and develop creative visual experiences but training them is difficult due to the complexity and size of video datasets. To overcome this the authors present a scalable open source pipeline using NVIDIA NeMo for training and inference of video foundation models. The pipeline provides accelerated video dataset curation multimodal data loading and parallelized video diffusion model training and inference. The authors also provide a comprehensive performance analysis highlighting best practices for efficient video foundation model training and inference. The pipeline is designed to address the challenges of training large scale video foundation models and provides a scalable and efficient solution for generating high quality videos. The results of the paper demonstrate the effectiveness of the pipeline in training video foundation models and provide insights into the best practices for efficient training and inference. Overall the paper contributes to the development of video foundation models by providing a scalable and efficient pipeline for training and inference.

📅 Published on Mar 17, 2025

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2503.12964
• PDF: https://arxiv.org/pdf/2503.12964

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

#VideoFoundationModels #NVIDIANeMo #VideoDatasetCuration #MultimodalLearning #VideoDiffusionModels

💥 #Cisco Certification Journey Starts Here!
Want to become a certified Network Engineer and boost your IT career in 2026? 🚀
Whether you're preparing for #CCNA #CCNP or even #CCIE, this is your chance to get premium Cisco learning resources & insider study support!

🔥 What You’ll Get:
🌐 Cisco Training Roadmaps
🌐 Networking Lab Guides
🌐 Command Cheat Sheets
🌐 Cisco Official eBooks
🌐 Real Practice Questions
🌐 Exam Preparation Tips

🎁 FREE Starter Resources Available:
🔗✅ CCNA Beginner Notes:https://reurl.cc/j6bqey
🔗✅ CCNP Study Checklist:https://reurl.cc/npWnbn

📩 To receive all FREE Cisco materials directly in your inbox:
wa.link/8i0msc
👉 Connect us and Leave your email to get instant access!

💡 Bonus for subscribers:
https://chat.whatsapp.com/FLth69u2WswIlZ6bta2SJf
✔ Exclusive study group invitations
✔ Latest Cisco exam changes
✔ Fast-track learning strategies
✔ Priority access to upcoming training sessions

⚡ Thousands of IT learners are already preparing smarter.
Don’t miss your chance to level up your networking career in 2026! 🚀

🔥 Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

💡 The paper introduces Agents-A1, a 35 billion parameter Mixture-of-Experts Agentic Model that achieves performance comparable to trillion-parameter models by scaling the agent horizon instead of the parameters. The problem addressed is how to improve the performance of large language models on long-horizon tasks without increasing the number of parameters. The method used is a three-stage training approach, which includes supervised fine-tuning, domain-level teacher models, and multi-teacher distillation. The model is trained on a long-horizon knowledge-action infrastructure that connects external knowledge, actions, observations, and verifier outcomes, producing agentic trajectories with an average length of 45,000 tokens. The results show that Agents-A1 achieves strong and broad performance on long-horizon agent benchmarks, outperforming or matching the results of 1 trillion parameter models on several tasks, including SEAL-0, IFBench, HiPhO, FrontierScience-Olympiad, and MolBench-Bind. The paper provides a practical path for scaling the horizon using a smaller model that can reach or match the performance of larger models on long-horizon tasks.

📅 Published on Jun 29

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.30616
• PDF: https://arxiv.org/pdf/2606.30616
• Project Page: https://internscience.github.io/Agents-A1/

🤖 Models citing this paper:
• https://huggingface.co/InternScience/Agents-A1
• https://huggingface.co/InternScience/Agents-A1-FP8-dynamic
• https://huggingface.co/Abiray/Agents-A1-Q4_K_M-GGUF

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

#MixtureOfExperts #AgenticModels #LongHorizonTasks #LargeLanguageModels #ParameterEfficientTraining

🔥 LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

💡 The paper introduces a novel streaming video editing framework called LiveEdit that enables real-time editing of videos with stable backgrounds and non-edited regions over time. The main challenge in streaming video editing is maintaining stable backgrounds and non-edited regions while achieving low latency for real-time interactive scenarios. Existing streaming video generation methods are not suitable for editing due to the strict preservation requirement and region-specific control.

To address this issue, the authors propose a three-stage distillation pipeline that transfers editing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming editor. This pipeline enables stable long-horizon edits without sacrificing visual fidelity. Additionally, the authors introduce an AR-oriented mask cache that reuses region-related computation across frames, reducing redundant processing and accelerating inference.

The results show that the proposed method achieves state-of-the-art visual quality among streaming baselines and drastically boosts inference speed to 12.66 frames per second. This makes it suitable for interactive and augmented reality applications. The authors also establish a dedicated benchmark for streaming video editing to evaluate their method. Overall, the paper presents a significant contribution to the field of streaming video editing by providing a real-time and stable editing framework.

📅 Published on Jun 25

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.26740
• PDF: https://arxiv.org/pdf/2606.26740
• Project Page: https://arxiv.org/abs/2606.26740

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/multimodalart/LiveEdit

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

#VideoEditingTechniques #RealTimeStreaming #DiffusionBasedEditing #StreamingVideoGeneration #LowLatencyEditing

🔥 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

🔥 PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

💡 The paper proposes PhysisForcing, a framework for enhancing the physical consistency of embodied video generation models for robotic manipulation. The problem with existing video generation models is that they can produce physically implausible manipulations, such as discontinuous motion trajectories and inconsistent robot-object interactions. This is mainly due to the deformation of moving objects and implausible spatio-temporal correlations among interacting entities, particularly during contact.

To address this issue, PhysisForcing uses a scalable training framework that focuses supervision on physics-informative regions through joint optimization of pixel-level and semantic-level features. The framework consists of two losses: a pixel-level trajectory alignment loss that supervises features using reference point trajectories, and a semantic-level relational alignment loss that aligns features with inter-region relations extracted from a frozen video understanding encoder.

The method is evaluated on several benchmarks, including R-Bench, PAI-Bench, and EZS-Bench, and the results show that PhysisForcing consistently improves embodied video generation over strong baselines. Specifically, it improves the Wan2.2-I2V-A14B and Cosmos3-Nano base models on R-Bench by 22.3% and 9.2%, respectively, with the Cosmos3-Nano variant attaining the best overall score.

Furthermore, the paper demonstrates that PhysisForcing can be used as a world model under the WorldArena action-planner protocol, which raises the closed-loop success rate from 16.0% to 24.0% and further improves downstream policy success. This indicates that physically aligned video models yield stronger representations for robotic manipulation. Overall, the paper contributes a novel framework for enhancing the physical consistency of embodied video generation models, which has the potential to improve the reliability and performance of robotic manipulation systems.

📅 Published on Jun 26

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2606.28128
• PDF: https://arxiv.org/pdf/2606.28128
• Project Page: https://dagroup-pku.github.io/PhysisForcing.github.io/

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

#RoboticsAndComputerVision #PhysicsInformedMachineLearning #RoboticManipulation #EmbodiedAI #ComputerVisionForRobotics

🔥 GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)

💡 The paper introduces GenericAgent, a self-evolving large language model agent system designed to overcome the limitations of long-horizon interactions. The main problem addressed is that as interactions become longer, the accumulation of tool descriptions, memories, and environmental feedback pushes out the information needed for decision-making, leading to poor performance. The authors argue that the key to improving long-horizon performance is not the length of the context, but rather how much decision-relevant information is maintained within a finite context budget.

To address this problem, the GenericAgent system is built around the principle of context information density maximization. The system consists of four main components: a minimal atomic tool set, a hierarchical on-demand memory, a self-evolution mechanism, and a context truncation and compression layer. The minimal atomic tool set keeps the interface simple, while the hierarchical on-demand memory only shows a small high-level view by default. The self-evolution mechanism turns verified past trajectories into reusable standard operating procedures and executable code, allowing the agent to learn from its experiences. The context truncation and compression layer maintains information density during long executions by removing unnecessary information.

The results show that GenericAgent consistently outperforms leading agent systems in terms of task completion, tool use efficiency, memory effectiveness, self-evolution, and web browsing. Moreover, GenericAgent achieves these results while using significantly fewer tokens and interactions, demonstrating its efficiency. The system also continues to evolve over time, allowing it to adapt to new situations and improve its performance. Overall, the paper presents a novel approach to building self-evolving large language model agents that can effectively handle long-horizon interactions and maximize context information density.

📅 Published on Apr 18

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2604.17091
• PDF: https://arxiv.org/pdf/2604.17091

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

#TokenEfficientLLMs #SelfEvolvingAgents #ContextualInformationDensity #LargeLanguageModelAgents #LongHorizonInteractions

🔥 An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU

💡 The paper addresses the challenge of fine-tuning large language models on single GPUs, which is limited by the models' memory-intensive nature. To overcome this, the authors propose SlideFormer, a system designed for single-GPU environments. The key innovations of SlideFormer include a lightweight asynchronous engine that overlaps GPU computation with CPU updates and multi-tier I/O, a heterogeneous memory management scheme that reduces peak memory usage, and optimized kernels that solve key bottlenecks and integrate advanced I/O.

The asynchronous engine treats the GPU as a sliding window, allowing for efficient processing. The heterogeneous memory management scheme significantly reduces memory usage, making it possible to fine-tune larger models. The optimized kernels improve performance by solving key bottlenecks and integrating advanced I/O.

The results show that SlideFormer achieves higher throughput and reduced memory usage compared to baselines. Specifically, it supports up to 8 times larger batch sizes and 6 times larger models, and achieves 1.40 to 6.27 times higher throughput while roughly halving CPU and GPU memory usage. The system sustains over 95 percent peak performance on both NVIDIA and AMD GPUs, demonstrating its effectiveness and efficiency. Overall, SlideFormer enables the fine-tuning of large language models on single GPUs, making it a significant contribution to the field of natural language processing.

📅 Published on Mar 17

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2603.16428
• PDF: https://arxiv.org/pdf/2603.16428

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

#HeterogeneousCoDesign #GPUMemoryOptimization #LanguageModelFineTuning #SingleGPUComputing #AsynchronousProcessingTechniques