AI & ML Papers

🔥 DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

💡 The paper introduces DataFlex, a unified framework for dynamic data-centric training of large language models. The problem addressed is that existing approaches to data selection, data mixture optimization, and data reweighting are often developed in isolated codebases, making it difficult to reproduce, compare, and integrate them. DataFlex solves this problem by providing a unified framework that supports three major paradigms of dynamic data optimization: sample selection, domain mixture adjustment, and sample reweighting. The method involves building DataFlex upon the LLaMA-Factory framework, which allows for extensible trainer abstractions and modular components. This enables a drop-in replacement for standard large language model training and unifies key model-dependent operations such as embedding extraction, inference, and gradient computation. DataFlex is also compatible with large-scale settings, including DeepSpeed ZeRO-3. The results show that DataFlex provides an effective, efficient, and reproducible infrastructure for data-centric dynamic training of large language models. Comprehensive experiments demonstrate that dynamic data selection consistently outperforms static full-data training, and data mixture methods improve both accuracy and perplexity over default proportions. Additionally, DataFlex achieves consistent runtime improvements over original implementations. Overall, the paper contributes a unified framework that enables efficient large-scale deployment of data-centric dynamic training methods for large language models.

📅 Published on Mar 27 🔗 Links: • GitHub: https://github.com/huggingface • arXiv: https://arxiv.org/abs/2603.26164 • PDF: https://arxiv.org/pdf/2603.26164 • Project Page: https://opendcai.github.io/DataFlex-Doc/en/ ━━━━━━━━━━━━━━━━━━━━━━━━ 📢 By: https://t.me/PaperNexus #LargeLanguageModels #DataCentricTraining #DynamicTrainingMethods #LanguageModelOptimization #DataDrivenAI

🔥 Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

💡 The paper introduces a new framework called Skill Self-Play that aims to improve the capability of large language models through co-evolving skills. The existing self-evolutionary methods face a dilemma between task diversity and verification reliability, where environment-bound methods provide precise feedback but confine learning to narrow domains, while open-ended self-generation broadens the task space but lacks reliable verification. The proposed framework identifies agent skills as a middle ground to reconcile this tension, ensuring deep and verifiable execution in specific scenarios while maintaining open-ended task variety through dynamic routing across skills. The Skill Self-Play framework consists of a proposer, a solver, and a dynamic skill controller, which co-evolve in a continuous self-play loop orchestrated by a reinforcement learning loop. The proposer generates challenging tasks conditioned on dynamically sampled skills, the solver explores candidate solutions to push its capability boundaries, and the skill controller collects execution feedback to update and expand the skill library. The empirical evaluations on tool-use and reasoning benchmarks demonstrate that Skill Self-Play effectively bridges the gap between structured verification and open-ended exploration, consistently pushing the performance ceiling of competent backbones while catalyzing striking turnarounds for initially misaligned models. The framework serves as a robust evolution engine, and the code is available for further research and development. Overall, the paper contributes a novel approach to improve the capability of large language models through co-evolving skills, addressing the long-standing dilemma between task diversity and verification reliability in self-evolutionary methods.

📅 Published on Jul 24 🔗 Links: • GitHub: https://github.com/huggingface • arXiv: https://arxiv.org/abs/2607.22529 • PDF: https://arxiv.org/pdf/2607.22529 ━━━━━━━━━━━━━━━━━━━━━━━━ 📢 By: https://t.me/PaperNexus #LargeLanguageModels #CoEvolvingSkills #SkillSelfPlay #LanguageModelTraining #ArtificialIntelligenceAdvances

Ref By Ref Chat PROMOTE YOUR LINK💻 In my chat channel you can send your own links to advertising and together we can earn money from it. 💸💰 #ad 📢 InsideAd

🔥 Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

💡 The paper introduces Molt, a scalable PyTorch-native training framework for agentic reinforcement learning. The problem addressed is the high cost of modifying algorithms, estimators, pipelines, and rollout schemes in existing frameworks, which can lead to significant overhead for researchers. Molt aims to keep this cost small by providing a compact and clean codebase that is easy for researchers to understand and modify. The method involves designing Molt as a PyTorch-native framework, where the agent is an ordinary program that can train multi-modal and mixture-of-experts policies in a single asynchronous loop. This approach allows for consistent tokenization, policy versions, and model semantics, without requiring the agent to train on tokens it did not generate. The results show that Molt is statistically comparable to a state-of-the-art Megatron-based stack, even when using an unmatched, fully asynchronous protocol. This demonstrates that the lean design of Molt does not come at the cost of performance. Additionally, Molt is open-source and provides recipes and containers, making it accessible to researchers and practitioners. Overall, the paper contributes a novel framework for agentic reinforcement learning that prioritizes simplicity, flexibility, and performance. By providing a clean and compact codebase, Molt enables researchers to easily modify and extend the framework, reducing the overhead associated with algorithmic changes and promoting faster innovation in the field.

📅 Published on Jul 22 🔗 Links: • GitHub: https://github.com/huggingface • arXiv: https://arxiv.org/abs/2607.21653 • PDF: https://arxiv.org/pdf/2607.21653 ━━━━━━━━━━━━━━━━━━━━━━━━ 📢 By: https://t.me/PaperNexus #AgenticReinforcementLearning #PyTorchNativeFrameworks #ScalableTrainingFrameworks #ReinforcementLearningAlgorithms #MixtureOfExpertsPolicies

Unlock Your Romance Goals! Stop right there! 💖 Are you ready to elevate your relationship? - Discover heartwarming moments that you both can vibe with! 🥰 - Experience cozy scenes that make you feel all the feels. 🌟 - Dive into your own love journey and create unforgettable memories. 💏 Don’t miss out-join our loving community today! 👉 Join the magic! #ad 📢 InsideAd

🔥 Efficient Reasoning with Balanced Thinking

💡 The paper Efficient Reasoning with Balanced Thinking proposes a training-free framework called ReBalance to address the issues of overthinking and underthinking in large reasoning models. Overthinking occurs when models expend redundant computational steps on simple problems, while underthinking happens when models fail to explore sufficient reasoning paths despite their inherent capabilities. These issues lead to inefficiencies and potential inaccuracies, limiting practical deployment in resource-constrained settings. The ReBalance framework leverages confidence as a continuous indicator of reasoning dynamics to identify overthinking and underthinking behaviors. It computes a steering vector to guide the models reasoning trajectories by aggregating hidden states from a small-scale dataset into reasoning mode prototypes. A dynamic control function modulates the steering vectors strength and direction based on real-time confidence, pruning redundancy during overthinking and promoting exploration during underthinking. The authors conducted extensive experiments on four models ranging from 0.5B to 32B and across nine benchmarks in math reasoning, general question answering, and coding tasks. The results demonstrate that ReBalance effectively reduces output redundancy while improving accuracy, offering a general, training-free, and plug-and-play strategy for efficient and robust large reasoning model deployment. The framework achieves efficient reasoning with balanced thinking, making it a valuable contribution to the field of artificial intelligence and natural language processing.

📅 Published on Mar 12 🔗 Links: • GitHub: https://github.com/huggingface • arXiv: https://arxiv.org/abs/2603.12372 • PDF: https://arxiv.org/pdf/2603.12372 • Project Page: https://rebalance-ai.github.io 🤖 Models citing this paper: • https://huggingface.co/Yulin-Li/ReBalance • https://huggingface.co/openpangu/openPangu-Embedded-7B-V1.1 ━━━━━━━━━━━━━━━━━━━━━━━━ 📢 By: https://t.me/PaperNexus #EfficientReasoning #BalancedThinking #OverthinkingInAI #UnderthinkingInAI #ReBalanceFramework

🔥 MediaPipe: A Framework for Building Perception Pipelines

💡 The paper introduces MediaPipe, a framework designed to simplify the development of perception applications. Building such applications is challenging due to the need to select and develop machine learning algorithms and models, create prototypes and demos, balance resource consumption with solution quality, and identify and mitigate problematic cases. MediaPipe addresses these challenges by providing tools for combining existing perception components, prototyping, and measuring performance across different platforms. The framework allows developers to build prototypes by combining components, advance them to polished cross-platform applications, and measure system performance and resource consumption on target platforms. This enables developers to focus on algorithm or model development and use MediaPipe as an environment for iteratively improving their application, with results that are reproducible across different devices and platforms. The key contribution of MediaPipe is that it facilitates the development of perception applications by providing a framework for combining components, prototyping, and measuring performance, thereby simplifying the development process and enabling developers to focus on core aspects of their applications. The framework will be made available as an open-source resource, allowing developers to access and utilize it for their projects. Overall, MediaPipe has the potential to streamline the development of perception applications and improve the efficiency of the development process.

📅 Published on Jun 14, 2019 🔗 Links: • GitHub: https://github.com/huggingface • arXiv: https://arxiv.org/abs/1906.08172 • PDF: https://arxiv.org/pdf/1906.08172 🚀 Spaces citing this paper: • https://huggingface.co/spaces/Jha-Pranav/PixelCare ━━━━━━━━━━━━━━━━━━━━━━━━ 📢 By: https://t.me/PaperNexus #MachineLearningFrameworks #PerceptionPipelines #CrossPlatformDevelopment #ComputerVisionApplications #MediaPipeFramework

This channels is for Programmers, Coders, Software Engineers. 0️⃣ Python 1️⃣ Data Science 2️⃣ Machine Learning 3️⃣ Data Visualization 4️⃣ Artificial Intelligence 5️⃣ Data Analysis 6️⃣ Statistics 7️⃣ Deep Learning 8️⃣ programming Languages ✅ https://t.me/addlist/8_rRW2scgfRhOTc0 ✅ https://t.me/Codeprogrammer

Did you know you can grow your income simply by completing tasks? Join TaskVerse today! 🌟 Earn online by tapping into various tasks that pay in cryptocurrency. With our fast withdrawal process, your earnings will be in your wallet before you know it! 💰 - 🌍 Global Reach: Work from anywhere, anytime! - 🔗 Promote your brand: Get real users engaged with your content. - 🤝 Referral Rewards: Invite friends and earn 10% on their activations! Start earning now: Earn More. Grow Faster. 👉 #ad 📢 InsideAd

🔥 Native and Compact Structured Latents for 3D Generation

💡 This paper addresses the challenge of 3D generative modeling where existing representations struggle to capture complex topologies and detailed appearance of 3D assets. To overcome this, the authors introduce a new sparse voxel representation called O-Voxel, which encodes both geometry and appearance of 3D objects. O-Voxel can robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfaces, and captures comprehensive surface attributes. The authors design a Sparse Compression VAE based on O-Voxel, which provides a high spatial compression rate and a compact latent space. They train large-scale models with 4B parameters on diverse public 3D asset datasets and achieve highly efficient inference. The results show that the generated assets have significantly better geometry and material quality compared to existing models. The approach offers a significant advancement in 3D generative modeling by enabling high-quality generation with efficient inference and robust topology handling.

📅 Published on Dec 16, 2025 🔗 Links: • GitHub: https://github.com/huggingface • arXiv: https://arxiv.org/abs/2512.14692 • PDF: https://arxiv.org/pdf/2512.14692 • Project Page: https://microsoft.github.io/TRELLIS.2/ 🤖 Models citing this paper: • https://huggingface.co/microsoft/TRELLIS.2-4B • https://huggingface.co/mancub/TRELLIS.2-4B • https://huggingface.co/Jinstudio/TRELLIS.2-4B 📊 Datasets citing this paper: • https://huggingface.co/datasets/serpentine-b/t2 🚀 Spaces citing this paper: • https://huggingface.co/spaces/microsoft/TRELLIS.2 • https://huggingface.co/spaces/TencentARC/Pixal3D • https://huggingface.co/spaces/broyang/3dai ━━━━━━━━━━━━━━━━━━━━━━━━ 📢 By: https://t.me/PaperNexus #3DGenerativeModeling #SparseVoxelRepresentation #CompactLatentSpace #3DAssetGeneration #GeometricDeepLearning

🔥 Color Pass-Through via Camera-Display Coupling

💡 The paper Color Pass-Through via Camera-Display Coupling addresses the issue of color discrepancy between the original scene and its displayed image on a smartphone screen. Despite advances in camera and display technology, the displayed image often differs noticeably from the original scene in terms of color, brightness, and contrast. This is because most pipelines separate the high-dimensional capture-to-display process into two stages, calibrating the camera and display separately and then connecting them through low-dimensional color transforms, which leads to information bottlenecks and error accumulation. To overcome this challenge, the authors propose Color Pass-Through, an end-to-end learned framework that operates directly on captured images. The key insight is to treat the camera and display as a coupled system rather than calibrating them in isolation. By coupling the camera and display, the authors achieve two practical advantages: it brings the entire real-world scene to the display via end-to-end optimization, and it allows for efficient one-step calibration for each distinct observer via the complete capture-to-display path. The authors validate Color Pass-Through using both digital and human observers. Compared to representative baselines, their method achieves an average gain of 2.0 points on a 5-point user study and more than 2x improvement on quantitative metrics, demonstrating improved reproduction of the perceived color of the original scene. The results show that the proposed approach can effectively reduce the color discrepancy between the original scene and its displayed image, leading to a more accurate and faithful representation of the scene.

📅 Published on Jul 14 🔗 Links: • GitHub: https://github.com/huggingface • arXiv: https://arxiv.org/abs/2607.12746 • PDF: https://arxiv.org/pdf/2607.12746 • Project Page: https://lyricccco.github.io/color-pass-through/ ━━━━━━━━━━━━━━━━━━━━━━━━ 📢 By: https://t.me/PaperNexus #ColorPassThrough #CameraDisplayCoupling #ColorDiscrepancyCorrection #DisplayColorCalibration #CaptureToDisplayProcessing

Unlock vast earning potential today! Join BINASOU4💸CHANNEL and discover how to maximize your profits through community love and empowerment. - Engage in exciting rewards and giveaways! 🎁 - Participate in exclusive Q&A sessions on Binance Square for a chance to win crypto boxes! - Collaborate with our supportive family and share insights that elevate your trading experience. - Stay updated on contests and activities that strengthen our cherished community. Don’t miss out on being part of something special. Your journey to increased profits starts here! 👉 Become a member now! #ad 📢 InsideAd

🔥 Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

💡 The paper addresses the issue of document set selection and ranking, which is crucial for large language models and AI agents that rely on search results. Existing evaluation systems score documents independently and aggregate them using metrics like DCG, ignoring interactions between documents such as redundancy, conflict, and complementarity. This limitation makes it difficult to determine what makes one document set better than another. To address this issue, the authors propose a comprehensive evaluate-diagnose-optimize framework. They design Setwise Eval Kit, a three-level, nine-dimension document set evaluation benchmark that covers both short-form and long-form scenarios, comprising approximately 28,000 high-quality evaluation rubrics. The authors systematically evaluate 12 rerankers and find that even the best method achieves no more than 45 percent coverage, and cross-document coordination dimensions are universally weak. No single method maintains top performance across both settings. Building on this, the authors propose Rubric4Setwise, a training-free method that converts rubric-based evaluation criteria into document set selection signals. This method achieves the best downstream generation performance with fewer documents and search rounds. It is the only method that maintains state-of-the-art results across both scenarios, validating the effectiveness of closing the loop from evaluation to optimization. The paper's contributions include a comprehensive evaluation framework, a new benchmark for document set evaluation, and a novel method for document set selection and ranking that outperforms existing methods. The results demonstrate the importance of considering cross-document interactions and using rubric-based evaluation criteria to improve document set selection and ranking.

📅 Published on Jul 22 🔗 Links: • GitHub: https://github.com/huggingface • arXiv: https://arxiv.org/abs/2607.19747 • PDF: https://arxiv.org/pdf/2607.19747 • Project Page: https://rubric4setwise.github.io/ ━━━━━━━━━━━━━━━━━━━━━━━━ 📢 By: https://t.me/PaperNexus #DocumentSetSelection #RubricOrientedRanking #InformationRetrieval #DocumentEvaluation #SetwiseOptimization