Hugging Face daily papers, ranked by community upvotes. Summaries and key terms are written by Workers AI from the abstract — click a term to filter, or search below (matches full abstracts and authors too).
This paper presents a video world model that can interact with a virtual environment in real-time, using a single desktop GPU. Practitioners might care about the potential applications of this technology in areas like virtual reality, gaming, and robotics.
This paper develops a new approach to understanding videos by predicting when specific events or evidence occur within the video. Practitioners working on video analysis and AI models might care about this research because it could lead to more accurate and robust video understanding systems.
This paper develops a system to extract and represent skills from human-created resources like videos, code, and articles, allowing software agents to learn from these multimodal inputs. Practitioners might care about this work because it could enable more effective training of agents in various domains.
This paper introduces RAGU, an open-source GraphRAG engine that improves large language models with structured knowledge by separating extraction and consolidation, and trains a compact extractor that outperforms larger models on knowledge-graph construction and GraphRAG tasks. Practitioners might care because RAGU can efficiently generate more accurate and complete context for tasks like factoid-level evidence recall and multi-hop question answering.
This paper creates a platform to help large language models generate code for data pipelines, which can then be edited and used to automate data processing workflows. Practitioners might care about this because it can help reduce the time and cost of developing and maintaining these pipelines.
This paper introduces AREX, a self-improving agent that recursively refines its answers by verifying intermediate results and using the partially verified state to guide subsequent refinement, aiming to improve the efficiency of deep research. Practitioners might care about AREX's approach to reducing the cost of discovery and verification in complex research tasks.
This paper introduces a framework called DeepSearch-Evolve, which helps train self-improving web agents by iteratively refining their performance using their own experience. Practitioners might care because this approach can lead to more efficient and effective agents that can learn from their own mistakes.
This paper introduces a framework called EvolvingWorld that allows characters and worlds to evolve together over time in interactive literary worlds, enabling more realistic and coherent simulations. Practitioners interested in developing more immersive and dynamic interactive stories might care about this approach.
This paper introduces a faster version of a generative world renderer that can run in real-time, allowing for interactive play and user control. A practitioner might care about this if they want to create immersive games or simulations.
This paper helps us understand how text-to-image diffusion transformers work by analyzing the role of "template tokens" in generating images from text prompts. Practitioners might care because it shows how to improve the efficiency of these models without sacrificing their performance.
This paper proposes a new pruning method for coding agents that prunes tool outputs directly inside the agent, rather than relying on a separate code classifier, and shows it can save up to 39% of tokens while preserving task quality.
This paper introduces Open-AoE, an open dataset and toolchain for egocentric manipulation learning, providing a scalable and structured platform for training embodied models. Practitioners can use Open-AoE to improve their robot learning models, especially those focused on human-robot interaction and embodied intelligence.
This paper introduces Mage-Flow, a compact model for generating and editing high-resolution images, which can be trained efficiently and deployed on a single GPU. Practitioners might care about the potential applications of this model in interactive image editing and generation tasks.
This paper introduces a vision-language-action model that can perform mobile manipulation tasks in unseen environments with minimal training data, and how it can be scaled up to achieve better performance. Practitioners might care about this model for building robots that can adapt to new tasks with minimal fine-tuning.
This paper optimizes the training of massive neural networks on a special-purpose hardware, the Ascend SuperPOD, to improve performance and stability. Practitioners in AI/ML model training might care about the techniques and results presented here for large-scale model training on non-GPU hardware.
This paper develops a video personalization method that focuses on human-object interactions, aiming to improve the accuracy of video generation by better understanding human-object relationships and incorporating intra-subject references. Practitioners may care about this research as it could lead to more realistic and engaging video content.
This paper develops a system called AlayaWorld that can generate interactive virtual worlds from text, images, or videos, allowing for customizable and evolving environments. Practitioners in areas like game development, virtual reality, or interactive storytelling might care about this research for its potential to streamline the creation of immersive experiences.
This paper proposes a new approach for embodied visual tracking that first identifies a target described in natural language and then tracks it using a single camera. Practitioners in robotics and autonomous systems might care about this work because it shows promise for robust and reliable visual tracking in real-world applications.
This paper introduces a benchmark to evaluate video generation models' ability to reason about physical laws, which is crucial for creating reliable world simulators. Practitioners caring about developing more realistic and physically intelligent AI models will find this research valuable.
This paper introduces a new framework for training educational language models, specifically designed to evaluate their ability to understand curriculum knowledge and its visual presentation. Practitioners might care about this work because it aims to improve language models' performance in educational settings.
This paper introduces Visual Contrastive Self-Distillation, a method that removes the need for external teacher information and privileged answers in on-policy self-distillation, allowing for simpler and more efficient learning. Practitioners might care about this approach because it can lead to better performance in language models.
This paper investigates how Diffusion Language Models (DLMs) internally represent time and how this representation can be used to modulate the model's behavior. Practitioners might care because understanding how DLMs process time could lead to more controllable and interpretable models.
This paper develops a framework to evaluate spatial cognition in image-generation models by asking them to draw or mark answers in a visual space, rather than relying on text-based inputs. Practitioners might care about this research to better understand how image-generation models think spatially and to improve their performance on tasks that require spatial reasoning.
This paper develops a large audio language model that can answer questions with specific timestamps, improving its ability to understand long audio recordings. Practitioners in audio and speech recognition may care about this development as it enables more accurate and context-specific information retrieval from audio data.
This paper introduces RynnBrain 1.1, a family of large-scale embodied foundation models that can perform tasks like spatial reasoning, localization, and planning, and shows promising results in real-world robot experiments. Practitioners may care about the potential of these models for robot manipulation and control.
This paper creates a new AI model that can edit and generate videos without needing masks, and can also learn to mimic image editing capabilities. Practitioners might care about this because it could lead to more diverse and realistic video editing data, and enable AI models to understand and generate human-like video editing instructions.
This paper develops a new method to improve the stability of asynchronous reinforcement learning by adapting the trust region to account for staleness, which is a common problem in this field. Practitioners might care about this because stable reinforcement learning can lead to better performance and more efficient training.
This paper develops a multilingual speech recognition model for underrepresented languages, addressing the issue of data scarcity and uneven performance, and shows promising results in controlled comparisons.
This paper proposes a new training method for autoregressive video diffusion models called Self Gradient Forcing, which helps them better remember and use past information to generate future frames. Practitioners might care about this because it could lead to more realistic and stable video extrapolation.
This paper develops a new framework for evaluating and selecting document sets for AI agents, considering the interactions between documents, and proposes a training-free method that achieves the best downstream generation performance with fewer documents and search rounds.
This paper proposes a new type of AI system that can watch and remember things over long periods, and use that memory to reason about the world. Practitioners might care because this could lead to more capable assistants that can learn and adapt over time.
This paper proposes a new method for reinforcement learning in large language models, called Group Entropy-Controlled Policy Optimization (GEPO), which helps balance exploration and exploitation by controlling entropy levels across different tasks. Practitioners might care about GEPO because it can lead to more balanced and task-specific exploration levels.
This paper introduces SeerGuard, a safety framework that helps mobile GUI agents make safe decisions by predicting potential outcomes of their actions before they are executed. Practitioners caring about the safety of autonomous mobile agents might be interested in this research.
This paper introduces a benchmark called ActiveVision to measure whether large language models (LLMs) exercise active observation, and finds that current LLMs are not robust in this regard, performing poorly on tasks that require repeated visual perception.
This paper introduces a new method called REBASE that allows for training-free in-context segmentation, enabling the introduction of new object categories at inference time. Practitioners might care because it eliminates the need for retraining and reduces memory overhead, making it a more efficient approach for real-world applications.
This paper introduces Qwen-Music, a music generation model that can produce highly musical and high-fidelity songs from text descriptions and existing songs. Practitioners in music generation and AI may care about this research for its potential to create realistic and engaging music.
This paper introduces AgentDebugX, an open-source toolkit that helps debug and recover from failures in large language model (LLM) agents, making it easier to identify and fix errors. Practitioners can benefit from AgentDebugX as it provides a framework for detecting, attributing, and recovering from errors, which can improve the accuracy and reliability of LLM agents.
This paper develops a new framework, SciForma, to generate scientific diagrams that accurately represent research logic, which is crucial for scientific communication and methodology validation. Practitioners can benefit from SciForma's ability to ensure structural fidelity in diagram generation, which can improve the accuracy and reliability of scientific research.
This paper introduces a new framework for building AI agents in Python, allowing developers to write agents that are both deterministic and model-agnostic. Practitioners might care because this framework could simplify the development of reliable AI agents for various applications.
This paper proposes a new AI method to improve the way images are displayed on a screen, making them look more like the real world, and why a practitioner might care because better image display can improve how we interact with digital content.
This paper introduces Tencent WorkBuddy Bench, a benchmark for coding agents that tests their performance across multiple domains, including code, web, office, and security. Practitioners might care about this benchmark because it provides a standardized way to evaluate and compare the performance of coding agents.
This paper proposes a method to generate synthetic data for training API-calling agents without the need for an actual environment. This is useful for scalability, as collecting high-quality data at scale can be difficult. Practitioners might care about this approach because it could speed up the development of AI agents that can interact with APIs.
This paper develops a framework called NexForge that helps train more capable artificial agents by automatically generating a large number of tasks and training data, without requiring a lot of manual setup. Practitioners might care because it can improve the performance of their own agent models.
This paper investigates how Large Language Models (LLMs) handle dynamic user intent in conversations, where users' goals change over time, and finds that current LLMs struggle with this capability, leading to significant performance drops when evaluated in a more realistic setting.
This paper investigates the use of the Muon optimizer in reinforcement learning (RL) post-training and finds that it can significantly improve the success rate of RL agents, especially when combined with other techniques like policy optimization and advantage estimation. Practitioners in RL may care about this research to explore new ways to improve the performance of their agents.
This paper investigates using hypernetworks for large-scale knowledge injection into language models, a technique that can improve their ability to answer factual questions. Practitioners may care because it could lead to more accurate and scalable language models for applications like customer service or question-answering systems.
This paper proposes a new method for fine-tuning vision-language models on robot demonstrations to improve their performance on real-world tasks, by preventing the overwrite of pre-trained representations and aligning language and action predictions. Practitioners may care about this work because it aims to improve the generalizability and robustness of vision-language-action policies in real-world applications.
This paper introduces a new video diffusion transformer called SANA-Video 2.0 that can generate high-quality videos efficiently, using a hybrid approach that combines linear attention with attention residuals. Practitioners might care about this paper because it presents a scalable and efficient method for generating high-resolution videos.
This paper learns how to separate the motion in videos into two parts: the camera's movement and the objects' movements, allowing for more accurate and meaningful analysis of the video content. Practitioners might care because this can improve the performance of computer vision models on tasks like object tracking and motion analysis.
This paper evaluates whether language models can be used to generate molecules that fit specific 3D constraints, such as protein pockets and spatial relationships between molecules. Practitioners in the field of drug design might care about this research because it could lead to more efficient and effective methods for generating candidate molecules.
This paper addresses a problem in reinforcement learning (RL) where algorithms with PPO-Clip suffer from "exploration collapse", where they fail to explore new areas of the environment. The authors propose a new method called Riemannian Isometric Policy Optimization (RIPO) that helps to balance exploration and exploitation by using a more accurate geometric metric.
This paper develops a new method for generating high-fidelity 3D images of thin-shell objects, like garments, by learning a continuous surface representation. Practitioners caring about 3D generation and object modeling might care about this approach because it achieves better results with fewer computational resources.
This paper introduces S1-Omni, a unified AI model that can reason about scientific data, generate predictions, and create new scientific content, which could be useful for researchers and practitioners who need to analyze and understand complex scientific information.
This paper proposes a new method for advantage shaping in reinforcement learning called Contrastive Policy Optimization (CPO), which uses contrastive disagreement between reference-guided and vanilla generation distributions to indicate correctness. Practitioners might care because it can improve the effectiveness of reinforcement learning methods in generating correct responses.
This paper develops a new method for generating realistic hand-object interactions in 3D animation, combining appearance and motion to create smooth and believable movements. Practitioners in the field of computer animation and AI may care about this research for its potential to improve the realism and consistency of interactive simulations.
This paper proposes a new way for large language models to learn from feedback, allowing them to retain more detailed information about the quality of their responses and learn from it in a more nuanced way. Practitioners might care because this approach could lead to better performance on tasks where the model doesn't have a clear way to evaluate its own output.
This paper develops a method to transform video foundation models' representations into compact, reconstruction-capable, and generation-friendly video latents, which can be used in various generative modeling tasks. Practitioners can use VideoRAE to improve the performance of their models by leveraging the semantic and spatio-temporal structure captured by the frozen video foundation encoder.
This paper introduces AutoIndex, a framework that learns to transform raw documents into representations for retrieval systems, allowing for more flexible and effective indexing. Practitioners may care about AutoIndex because it can improve the quality of search results in complex information retrieval tasks.
This paper introduces a new method for generating videos in multi-agent environments, where each agent has its own view of the world. It's useful for applications like video games or simulations where multiple agents need to interact with each other and the environment.
This paper proposes a new method called Distilled Reinforcement Learning that improves large language model post-training by providing fine-grained guidance to transfer new knowledge from a teacher model to a student model. Practitioners might care because it outperforms standard reinforcement learning and on-policy distillation methods in terms of knowledge transfer and model performance.
This paper introduces HPD-Parsing, a new approach to document parsing that uses hierarchical parallel decoding to improve efficiency and throughput. Practitioners in natural language processing and computer vision might care because it could lead to faster and more accurate document parsing models.
This paper develops a more efficient way to generate high-quality videos by balancing the workload across multiple GPUs during training, which can improve the performance of video generation models like those used in FVAttn. Practitioners in video generation and deep learning might care about this research because it can lead to faster and more efficient video generation models.
This paper introduces Robostral Navigate, a vision-language model that enables robots to navigate using only a single monocular RGB camera, making it more scalable and cost-effective for deployment across various robotic platforms. Practitioners might care about this because it can simplify navigation tasks for robots in real-world environments.
This paper proposes a new method to improve reinforcement learning for large language models by using a predictive divergence mask, which helps stabilize off-policy updates. Practitioners caring about improving the stability and performance of LLM-based reinforcement learning might find this approach useful.
This paper introduces a benchmark framework called DocOps to evaluate autonomous agents' ability to manipulate digital documents. Practitioners may care about this work because it identifies limitations in current agents and provides insights for designing more robust agents.
This paper introduces ATSplat, a new method for 3D Gaussian Splatting that can efficiently synthesize novel views of scenes from a few images. ATSplat is faster and more efficient than previous methods, allowing for high-quality novel views to be rendered quickly.
This paper proposes a method to improve on-policy distillation by reusing pre-collected teacher data, allowing for faster training without interacting with the environment. Practitioners may care about this technique because it enables scalable and efficient distillation of complex agent models.
This paper develops a method called Experience Distillation that allows agents to learn from their own interaction histories without needing additional environment interactions, making learning more sample-efficient. Practitioners might care about this because it can improve the performance of agents in complex environments with limited resources.
This paper investigates where the optimizer state should be allocated in the context of mixture-of-experts training to reduce memory usage without sacrificing accuracy. Practitioners might care because optimizing memory usage can be crucial for large-scale language models.
This paper introduces a new framework to evaluate the factuality and completeness of long-form generation models, which is essential for ensuring that generated text is accurate and informative. Practitioners in natural language processing and artificial intelligence can benefit from this framework to assess the quality of their models.
This paper develops a new architecture for implicit neural representations (INRs) that uses sinusoidal recurrence to improve the quality of the representations, and it demonstrates that this approach can lead to better image and 3D representations with fewer parameters and less computation.
This paper develops a new type of artificial intelligence model that can simulate complex environments and make decisions in them, which could be useful for training robots and other agents to perform tasks in the real world. Practitioners might care because these models could help solve problems in areas like robotics, autonomous vehicles, and healthcare.
This paper proposes a new method for training language models to generate coherent and faithful responses, even when the input data has changed significantly. Practitioners might care about this research because it could lead to more robust and adaptable language models that can handle real-world scenarios where data distributions shift.
This paper improves the accuracy of Automatic Speech Recognition (ASR) models by controlling the style of the transcription, allowing for more reliable word-level timing and disfluency detection. Practitioners can benefit from this work to improve the quality of ASR systems in real-world applications.
This paper develops a new AI model, Delineate Anything v2, designed to accurately map large agricultural fields from satellite images. A practitioner might care about this because it can help ensure global food security and supply chain transparency by providing precise boundaries for fields.
This paper develops a new optimization framework called Isospectral Optimization (ISO) that improves the performance of language models trained using reinforcement learning with verifiable rewards (RLVR) by reusing the base model's weight spectra while adapting the input and output singular frames. Practitioners might care about this because it could lead to faster and more accurate training of large language models.
This paper develops a new method for cross-view geo-localization that uses video clips and route descriptions to improve accuracy, and introduces a unified framework that can handle both modalities. Practitioners in autonomous vehicle development or geospatial analysis might care about this research as it aims to address a common challenge in these fields.
This paper introduces H^2SD, a hybrid hindsight self-distillation framework for reinforcement learning with verifiable rewards, which combines the strengths of different methods to improve large language models' reasoning capabilities. Practitioners may care about this work because it addresses limitations of existing methods and shows promising results on challenging reasoning benchmarks.
This paper introduces a new environment called Trace, which allows vision-language models to reason across multiple domains and tasks, using a taxonomy-guided approach. Practitioners might care because this work could lead to more generalizable and transferable AI models.
This paper investigates whether large language models, like Google's Gemma-4-E4B-it, represent scientific concepts and governing physics, and whether this representation affects their answers. Practitioners caring about the accuracy and reliability of language models in scientific domains might find this research valuable.
This paper introduces TableVerse, a large-scale dataset of tabletop environments that are realistic, physically consistent, and suitable for training generalizable robotic manipulation policies. Practitioners can use this dataset to improve the performance of robots in tasks like pick-and-place manipulation.
This paper introduces ICAE-Bench, a benchmark for evaluating coding agents that can build software from incomplete product intent, simulating real-world interactive project-building settings. Practitioners in AI and software development may care about this research because it aims to create more realistic and challenging tests for coding agents.
This paper proposes a method to generate cinematic videos with coherent narratives and effective multi-shot composition by incorporating explicit shot planning into a video diffusion model. Practitioners might care about this because it could improve the quality and flexibility of video generation in applications like film and video production.
This paper develops a mathematical framework to analyze the Transformer architecture, using differential geometry to model its core components. Practitioners may care about this work because it provides new insights into the stability and optimization dynamics of Large Language Models.
This paper evaluates language models and deep-research agents at predicting football match outcomes before kickoff, using a dynamic benchmark that can be reused for future leagues. Practitioners can learn from the results to improve their own models' performance in similar tasks.
This paper develops a service-oriented framework, JoyNexus, to efficiently train and deploy Vision-Language-Action models across multiple tenants, improving resource utilization and reducing costs. Practitioners may care about JoyNexus for its potential to streamline the training process and make VLA models more accessible.
This paper evaluates the performance of security agents in a cost-aware way, considering not just their success rate but also the resources they use, to better understand which models are practical and useful in real-world security operations.
This paper helps prevent attackers from learning a negotiation agent's private constraints by analyzing how the agent makes decisions, and it proposes a new policy that balances privacy and performance. Practitioners might care about this research if they develop autonomous negotiation systems that could be vulnerable to attacks.
This paper proposes a way to improve vision-language-action models so they can better understand the world from a robot's perspective, which is important for robots to make accurate decisions. By using robot-centric pointmaps, these models can generalize better across different camera setups and viewpoints.
This paper introduces Agon, a method for training reinforcement learning models to improve their reasoning abilities by competing with each other, rather than just optimizing for the final answer. Practitioners may care about using this approach to improve the quality of reasoning in AI models.
This paper introduces EduPanel, a machine learning model that evaluates the quality of teaching videos in a more nuanced way than existing methods, and shows that it can provide reliable and interpretable assessments that complement human expertise.
This paper develops a new way to control video models, allowing them to understand how objects move in the world and how robots interact with them, which can be useful for robots that need to perform tasks in real-world environments. Practitioners in robotics and AI may care about this work because it could improve the ability of robots to understand and interact with their surroundings.
This paper proposes a method to improve the explainability of natural-language autoencoders by making it harder for models to manipulate the explanations, and shows that this approach can increase the reliability of activation explanations and improve AI safety.
This paper introduces a new method, Surrogate Latent Policy Optimization (SLPO), to improve the performance of autoregressive latent reasoners in reinforcement learning by combining outcome-reward RL with latent reasoning. Practitioners might care because SLPO can help scale the performance of these models at test time, which is currently a major challenge.
This paper introduces a new framework for generating synchronized multi-view RGB-T data for aerial object detection, which can help practitioners improve their object detection models by training on more realistic data and by reducing the need for expensive real-world data collection.
This paper creates a benchmark for testing the ability of AI agents to understand and analyze complex financial documents, and uses it to evaluate the performance of different agents in this task. Practitioners in finance and AI research can care about this work because it aims to improve the accuracy and reliability of financial document analysis.
This paper addresses a common issue in agentic language models where they may over-call tools, leading to suboptimal performance. A practitioner might care about this problem because it can negatively impact the model's ability to provide accurate and efficient responses.
This paper creates a benchmark to evaluate how well large language models can understand images from optical coherence tomography (OCT), a tool used to diagnose retinal diseases. Practitioners in medical imaging and AI might care because it could help improve the accuracy of AI models in diagnosing and treating retinal diseases.
This paper investigates how operating system (OS) defenses can prevent self-state attacks on self-hosted AI agents, which involve compromising an agent's own memory and configuration files. Practitioners caring about AI agent security should consider the limitations of current OS defenses against these types of attacks.
This paper introduces FlashRT, a tool that helps developers create efficient, real-time multimodal applications by guiding coding agents to optimize their deployments. Practitioners might care about FlashRT because it can significantly improve the performance of their applications, such as latency and throughput.