🔥 Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

💡 The paper addresses the challenge of multi-view 3D reconstruction under degraded conditions, where real-world observations often contain degradations that differ significantly from ideal settings. Traditional feed-forward 3D reconstruction models are typically trained and evaluated under ideal conditions and are not robust to degradations. To improve robustness, the authors propose a novel framework called Geometry-Aware Representation Denoising, or GARD.

GARD is a diffusion-based framework that operates in the feature space of a 3D reconstructor, exploiting the geometry-aware feature representations to effectively recover accurate scene geometry. The framework also employs an additional RGB image decoder to restore high-quality RGB images, enabling the simultaneous recovery of 3D scene geometry and high-quality imagery.

The authors evaluate the effectiveness of the proposed GARD framework through comprehensive experiments on the Depth Anything 3 benchmark. The results demonstrate that GARD can restore both scene geometry and high-quality imagery from degraded inputs, outperforming traditional methods. The paper contributes a novel approach to robust multi-view 3D reconstruction, improving the accuracy and quality of 3D scene geometry and imagery under degraded conditions.

📅 Published on May 25

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2605.26230
• PDF: https://arxiv.org/pdf/2605.26230
• Project Page: https://cvlab-kaist.github.io/GARD/

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

#GeometryAwareReconstruction #3DReconstructionRobustness #MultiViewGeometry #DiffusionBasedReconstruction #Robust3DSceneUnderstanding

🔥 CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

💡 The paper addresses the problem of training computer-use agents using reinforcement learning with verifiable rewards, which is limited by the scarcity of scalable training data with deterministic rewards. To solve this, the authors propose CUA-Gym, a scalable pipeline that generates task instructions, environment states, and reward functions. The pipeline consists of a generator agent, a discriminator agent, and an orchestrator agent that work together to create high-quality training data. The generated data is then filtered using a combination of large language model majority voting and agent rollouts to ensure quality.

To further address the scarcity of training environments, the authors create CUA-Gym-Hub, a suite of high-fidelity mock web applications that mimic real-world software-use distributions. Using this pipeline, the authors construct a dataset of 32,112 verified training tuples grounded in 110 environments. They then train two models, CUA-Gym-A3B and CUA-Gym-A17B, using the dataset and achieve state-of-the-art performance on the OSWorld-Verified benchmark, with scores of 62.1% and 72.6% respectively.

The results demonstrate that the proposed pipeline and dataset can be used to train computer-use agents that outperform prior models at comparable scales. Additionally, the models show transferability beyond the training environments, as they also improve on the held-out WebArena benchmark. The authors plan to open-source the full synthesis pipeline, dataset, environments, and models, making it possible for others to build upon their work and further advance the field of computer-use agents. Overall, the paper presents a significant contribution to the field of reinforcement learning and computer-use agents, providing a scalable and effective way to train agents that can perform complex tasks in a variety of environments.

📅 Published on May 25

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2605.25624
• PDF: https://arxiv.org/pdf/2605.25624
• Project Page: https://cua-gym.xlang.ai

📊 Datasets citing this paper:
• https://huggingface.co/datasets/xlangai/CUA-Gym

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

#ComputerUseAgents #VerifiableRewards #ReinforcementLearning #TaskInstructionGeneration #ScalableTrainingEnvironments

🔥 ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents

💡 The paper presents ProRL Agent, a scalable infrastructure for reinforcement learning training of multi-turn large language model agents. The problem addressed is the difficulty in generating and managing large numbers of sandboxed rollout trajectories required for reinforcement learning, which is a key component for improving the long-horizon behavior of these agents. Existing infrastructures often combine rollout orchestration with the training loop, making systems hard to migrate and maintain.

To solve this problem, the authors propose a rollout-as-a-service approach, where ProRL Agent serves the full agentic rollout lifecycle through an API service. This allows for decoupling rollout orchestration from the training loop, making the system more flexible and easier to maintain. Additionally, ProRL Agent provides standardized and extensible sandbox environments that support diverse agentic tasks in high-performance computing settings.

The authors validate ProRL Agent by applying it to reinforcement learning training on various tasks, including software engineering, math, STEM, and coding. The results demonstrate the effectiveness of ProRL Agent in supporting scalable and efficient reinforcement learning training. Furthermore, ProRL Agent is open-sourced and integrated as part of NVIDIA NeMo Gym, making it accessible to the research community. Overall, the paper contributes a scalable and flexible infrastructure for reinforcement learning training of multi-turn large language model agents, which can facilitate advancements in complex, interactive tasks.

📅 Published on Mar 19

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2603.18815
• PDF: https://arxiv.org/pdf/2603.18815

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

#ReinforcementLearning #LargeLanguageModels #MultiTurnDialogue #RolloutOptimization #RLTrainingInfrastructure

Found an easy way to learn math for ML: Mathematics for Machine Learning 🎓📚

This is a curated collection on GitHub, including books, research papers, video lectures, and basic materials on math for studying and reviewing the mathematical foundations of machine learning. 📖📊

It helps build a stronger knowledge base by bringing together trusted resources around topics that machine learning engineers constantly encounter: linear algebra, mathematical analysis, probability theory, statistics, information theory, matrix calculus, and deep learning mathematics. 🧮🤖

Free public repository on GitHub. 💻✨

https://github.com/dair-ai/Mathematics-for-ML

#MachineLearning #Mathematics #DataScience #Learning #GitHub #AI

🔥 Beyond Mode Collapse: Distribution Matching for Diverse Reasoning

💡 The paper addresses the problem of mode collapse in on-policy reinforcement learning, where methods like GRPO concentrate probability mass on a single solution and cease exploring alternative strategies. This is due to the reverse KL minimization method used, which reinforces the first high-reward trajectory found rather than maintaining a distribution over multiple diverse solutions. To solve this problem, the authors propose DMPO, a distribution-matching policy optimization method that uses forward KL minimization to maintain solution diversity and improve performance in combinatorial optimization and reasoning tasks. DMPO constructs a target distribution over sampled trajectories proportional to their rewards and aligns the policy distribution to this target, providing mode-covering behavior without requiring sampling from the intractable global target distribution. The authors validate DMPO on NP-hard combinatorial optimization tasks and achieve significant improvements over GRPO, with a 43.9 percent quality ratio on text-based tasks and 43.1 percent on vision-based tasks. These gains generalize to mathematical reasoning and out-of-domain tasks, demonstrating that diversity-preserving training enhances general reasoning capabilities across modalities. The results show that DMPO achieves consistent quality improvements and sustained exploration across diverse reasoning tasks, establishing distribution matching as a practical approach to preventing mode collapse in on-policy reinforcement learning.

📅 Published on May 19

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2605.19461
• PDF: https://arxiv.org/pdf/2605.19461

📊 Datasets citing this paper:
• https://huggingface.co/datasets/OliverLee/NP_MM

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

#ModeCollapseMitigation #DistributionMatching #OnPolicyReinforcementLearning #DiverseReasoningTasks #CombinatorialOptimizationTechniques

🔥 LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence

💡 The paper introduces LLaVA-OneVision-2, a vision-language model that achieves superior performance across various multimodal benchmarks. The problem addressed is the need for a more capable model that can efficiently process and understand video content. The method used to achieve this is codec-stream tokenization, which treats compressed video as a continuous bit-cost stream and allocates a limited token budget to event-bearing content. This approach enables more stable long-video token compression than fixed groups of pictures. The model also incorporates windowed attention for efficient local computation and a shared 3D RoPE to place codec canvases, sampled frames, and images in a unified spatiotemporal coordinate system.

The model was trained using large-scale open supervision, with approximately 8 million re-captioned video samples for pretraining and a 4 million sample spatial corpus for fine-tuning. The paper also introduces JumpScore, a temporal-localization benchmark that targets fine-grained grounding in high-frequency, densely repeated motion. The results show that LLaVA-OneVision-2 outperforms existing models, including Qwen3-VL-8B, by a significant margin. On the JumpScore benchmark, LLaVA-OneVision-2-8B reaches 74.9 JumpScore mAP, surpassing Qwen3-VL-8B by 44.8 points. The model also outperforms Qwen3-VL-8B by 4.3 average points on video tasks, 5.3 on spatial tasks, and 15.6 average J&F on tracking tasks.

The key contributions of the paper are the introduction of codec-stream tokenization, windowed attention, and large-scale open supervision, which enable the model to achieve superior performance across a broad range of multimodal benchmarks. The paper also highlights the importance of unified perception across video understanding, temporal grounding, spatial grounding, and manipulation-trace reasoning. Overall, the paper demonstrates the effectiveness of LLaVA-OneVision-2 in achieving next-generation perceptual intelligence.

📅 Published on May 25

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2605.25979
• PDF: https://arxiv.org/pdf/2605.25979
• Project Page: https://evolvinglmms-lab.github.io/LLaVA-OneVision-2/

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

#MultimodalLearning #VisionLanguageModels #VideoContentUnderstanding #PerceptualIntelligence #CodecStreamTokenization

🔥 Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

💡 The paper explores the design space for multimodal large language models that use a mixture of vision encoders and resolutions to improve performance. The goal is to accurately interpret complex visual information, which is crucial for tasks such as optical character recognition and document analysis. Recent work has shown that using multiple vision encoders can enhance visual perception and reduce hallucinations, but there is a lack of systematic comparisons and detailed ablation studies on this topic.

To address this, the authors conducted an extensive exploration of the design space for multimodal large language models using a mixture of vision encoders and resolutions. They found that simply concatenating visual tokens from a set of complementary vision encoders is as effective as more complex mixing architectures or strategies. They also introduced a Pre-Alignment mechanism to bridge the gap between vision-focused encoders and language tokens, which enhances model coherence.

The resulting family of multimodal large language models, called Eagle, surpasses other leading open-source models on major benchmarks. The authors discovered that their streamlined yet effective design approach is based on several underlying principles common to various existing strategies. The Eagle models and code are available online, providing a valuable resource for the research community. Overall, the paper contributes to the development of more effective multimodal large language models by providing a systematic exploration of the design space and introducing a simple yet effective design approach.

📅 Published on Aug 28, 2024

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2408.15998
• PDF: https://arxiv.org/pdf/2408.15998
• Project Page: https://huggingface.co/papers/2407.02392

🤖 Models citing this paper:
• https://huggingface.co/NVEagle/Eagle-X5-13B-Chat
• https://huggingface.co/NVEagle/Eagle-X5-7B
• https://huggingface.co/NVEagle/Eagle-X5-13B

📊 Datasets citing this paper:
• https://huggingface.co/datasets/shi-labs/Eagle-1.8M

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/merve/vision_papers
• https://huggingface.co/spaces/NVEagle/Eagle-X5-13B-Chat
• https://huggingface.co/spaces/shaktibiplab/Eagle-X5-13B-Chat

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

#MultimodalLLMs #MixtureOfEncoders #VisionEncoderDesign #OpticalCharacterRecognition #DocumentAnalysisModels

🔥 MOSS-TTS Technical Report

💡 The MOSS-TTS technical report presents a speech generation model that utilizes discrete audio tokens and autoregressive modeling to achieve voice cloning, pronunciation control, and long-form generation across multiple languages. The model is built on a scalable recipe that includes a causal Transformer tokenizer, which compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations. The report releases two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio.

The problem addressed by the report is the need for a speech generation model that can handle multilingual and open-domain settings, and support various features such as voice cloning, pronunciation control, and long-form generation. The method used to address this problem is the development of the MOSS-TTS model, which is built on a combination of discrete audio tokens, autoregressive modeling, and large-scale pretraining.

The results of the report show that the MOSS-TTS model supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation across multilingual and open-domain settings. The report also summarizes the design, training recipe, and empirical characteristics of the released models, providing a comprehensive overview of the MOSS-TTS model and its capabilities. Overall, the MOSS-TTS model presents a significant contribution to the field of speech generation, offering a scalable and efficient solution for a wide range of applications.

📅 Published on Mar 18

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2603.18090
• PDF: https://arxiv.org/pdf/2603.18090
• Project Page: https://mosi.cn/models/moss-tts

🤖 Models citing this paper:
• https://huggingface.co/OpenMOSS-Team/MOSS-TTS
• https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Nano-100M
• https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Realtime

📊 Datasets citing this paper:
• https://huggingface.co/datasets/somu9/mls_eng_tokens

🚀 Spaces citing this paper:
• https://huggingface.co/spaces/OpenMOSS-Team/MOSS-TTS-v1.5
• https://huggingface.co/spaces/OpenMOSS-Team/MOSS-TTS-Nano
• https://huggingface.co/spaces/OpenMOSS-Team/MOSS-TTS

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

#SpeechGeneration #VoiceCloning #AutoregressiveModeling #DiscreteAudioTokens #TransformerTokenizer

🔖 A huge open-source course on AI Engineering from scratch

In the repository, we've collected:
— 435 lessons;
— 320+ hours of content;
— Python, TypeScript, and Rust;
— AI agents, MCP servers, prompts, and AI skills.

Moreover, almost every lesson includes practical tasks, so this isn't just theory, but a full-fledged roadmap for AI Engineering. 🚀

⛓️ Link to the repository
https://github.com/rohitg00/ai-engineering-from-scratch

#AI #MachineLearning #Python #Rust #OpenSource #Tech

✨ Join Best TG Channels https://xn--r1a.website/addlist/0f6vfFbEMdAwODBk

⭐️ Join Our WhatsApp Channel https://whatsapp.com/channel/0029VaC7Weq29753hpcggW2A

🔥 OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning

💡 The paper introduces OSP-Next, an efficient text-to-video generation model that addresses the high computational costs of existing models. The problem with current models, such as Diffusion Transformers, is that they achieve strong video generation quality but have quadratic costs due to full attention. To solve this, OSP-Next combines sparse attention, parallelism, quantization, and reinforcement learning.

The method used in OSP-Next is a hybrid full-sparse attention architecture, where the sparse component is implemented with Skiparse-2D Attention. This mechanism applies token-wise and group-wise sparse attention along spatial dimensions, leveraging locality while maintaining compatibility with FlashAttention kernels. The authors also propose Sparse Sequence Parallelism, which partitions subsequences across ranks and switches sparse patterns through a single All-to-All communication. This approach reduces communication volume by 75% compared to Ulysses Sequence Parallelism.

Additionally, OSP-Next incorporates HiF8 quantization to enable stable joint training with 8-bit quantization and sparse fine-tuning. The model also applies Mix-GRPO post-training to improve the performance of the sparse model. The authors evaluate OSP-Next on various settings, including 5-second 720P and 5-second 768P, and achieve significant speedups on NVIDIA H200 GPUs and Ascend 950PR hardware.

The results show that OSP-Next achieves a VBench total score of 83.73%, surpassing the Wan2.1 baseline. The model achieves up to 1.64 times single-GPU speedup and over 1.52 times eight-GPU speedup on NVIDIA H200 GPUs. Furthermore, with only a 0.4% drop in VBench total score, OSP-Next-HiF8 achieves 1.69 times and 2.27 times speedups under the two settings on a single Ascend 950PR, demonstrating the efficiency and performance of OSP-Next across hardware platforms. Overall, the paper contributes to the development of efficient text-to-video generation models with high-quality video synthesis and reduced computational costs.

📅 Published on May 27

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2605.28691
• PDF: https://arxiv.org/pdf/2605.28691

🤖 Models citing this paper:
• https://huggingface.co/yunyangge/OSP-Next

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

#VideoGenerationModels #SparseSequenceParallelism #HiF8Quantization #ReinforcementLearningForVideo #TextToVideoSynthesis

🔥 DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

💡 The paper introduces DenoiseRL, a reinforcement learning framework that aims to improve reasoning in large language models by learning from incorrect reasoning traces. The problem with existing methods is that they rely heavily on stronger teacher models or carefully curated datasets, which limits their scalability and capability to improve. DenoiseRL addresses this issue by substituting external supervision with recovery-oriented optimization over failures from weak models. This approach allows the model to learn directly from incorrect reasoning traces, converting them into opportunities for improvement and making training more scalable and less dependent on external resources.

The method used in DenoiseRL involves failure-oriented optimization, where the model learns from its own mistakes and recovers from noisy prefixes. This approach yields a richer and more diverse learning signal, improving exploration efficiency from imperfect model behavior. As a result, DenoiseRL improves reasoning performance and overall training efficiency while reducing the need for expensive data curation or stronger teacher models.

The results of the paper show that DenoiseRL consistently outperforms strong on-policy RL baselines across competitive mathematical and general reasoning benchmarks. The framework also promotes stronger self-corrective behavior as training difficulty increases, highlighting an effective and scalable alternative pathway for improving reasoning in large language models. Overall, the paper contributes to the development of more efficient and scalable methods for improving reasoning in large language models, and demonstrates the potential of DenoiseRL as a framework for advancing reasoning capabilities in AI systems.

📅 Published on May 27

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2605.28421
• PDF: https://arxiv.org/pdf/2605.28421

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

#DenoiseRL #ReinforcementLearningForNLP #NoisyPrefixRecovery #ReasoningModelOptimization #LargeLanguageModelImprovement

🔥 stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation

💡 The paper introduces stable-worldmodel, a modular and standardized research framework for developing and evaluating world models. World models are a powerful tool for learning compact representations of environment dynamics, enabling agents to reason and generalize beyond direct experience. However, current implementations are often publication-specific, which limits their reusability, increases the risk of bugs, and reduces evaluation standardization.

To address this issue, the authors developed stable-worldmodel, a tested and documented research ecosystem that provides efficient data collection tools, standardized environments, planning algorithms, and baseline implementations. The framework allows for controllable environmental factors, including visual and physical properties, to support robustness and continual learning research.

The authors demonstrate the utility of stable-worldmodel by using it to study zero-shot robustness in DINO-WM. The framework provides a standardized way to evaluate world models, which can help to advance research in this area. The main contributions of the paper are the introduction of a modular and standardized research framework for world models, the provision of efficient data collection tools and standardized environments, and the demonstration of the framework's utility in studying zero-shot robustness.

Overall, the paper aims to provide a reliable and reproducible research framework for world modeling, which can help to accelerate progress in this field. The authors' goal is to enable researchers to focus on developing new world models and evaluating their performance, rather than spending time on implementing and debugging existing models. By providing a standardized framework, the authors hope to facilitate the development of more robust and generalizable world models that can be used in a variety of applications.

📅 Published on Feb 9

🔗 Links:
• GitHub: https://github.com/huggingface
• arXiv: https://arxiv.org/abs/2602.08968
• PDF: https://arxiv.org/pdf/2602.08968
• Project Page: https://galilai-group.github.io/stable-worldmodel/

🤖 Models citing this paper:
• https://huggingface.co/zzsi/swm-dmc-cheetah
• https://huggingface.co/zzsi/swm-dmc-expert-policies

📊 Datasets citing this paper:
• https://huggingface.co/datasets/zzsi/swm-dmc-expert
• https://huggingface.co/datasets/zzsi/swm-dmc-mixed-small
• https://huggingface.co/datasets/zzsi/swm-dmc-mixed-large

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

#WorldModeling #ReinforcementLearning #ArtificialIntelligence #RoboticsResearch #EnvironmentModeling