Trending Papers - Hugging Face

# Trending Papers - Hugging Face > Source: https://paperswithcode.com/learn Trending Papers - Hugging Face Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Website Tasks HuggingChat Collections Languages Organizations Community Blog Posts Daily Papers Hardware Learn Discord Forum GitHub Solutions Team & Enterprise Hugging Face PRO Enterprise Support Inference Providers Inference Endpoints Storage Buckets Log In Sign Up new Get trending papers in your email inbox once a day! Get trending papers in your email inbox! Subscribe Trending Papers by AK and the research community Daily Weekly Monthly Trending Papers Submitted by taesiri Infinite Worlds with Versatile Interactions An advanced world modeling system with extended interaction capabilities, real-time processing, diverse interactive elements, and multi-agent behavior control for collaborative virtual environments. Robbyant · Published on Jul 8, 2026 Upvote 29 GitHub 785 arXiv Page Submitted by taesiri Infinite Worlds with Versatile Interactions An advanced world modeling system with extended interaction capabilities, real-time processing, diverse interactive elements, and multi-agent behavior control for collaborative virtual environments. Robbyant · Jul 8, 2026 Upvote 29 GitHub 785 arXiv Page Submitted by taesiri Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence LingBot-Video presents a DiT-based video pretraining framework with Mixture-of-Experts architecture, specialized data augmentation, and multi-dimensional reward system for embodied intelligence applications. Robbyant · Published on Jul 8, 2026 Upvote 46 GitHub 672 arXiv Page Submitted by taesiri Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence LingBot-Video presents a DiT-based video pretraining framework with Mixture-of-Experts architecture, specialized data augmentation, and multi-dimensional reward system for embodied intelligence applications. Robbyant · Jul 8, 2026 Upvote 46 GitHub 672 arXiv Page AutoDev: Automated AI-Driven Development AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation. 5 authors · Published on Mar 13, 2024 Upvote 15 GitHub 19.9k arXiv Page AutoDev: Automated AI-Driven Development AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation. 5 authors · Mar 13, 2024 Upvote 15 GitHub 19.9k arXiv Page Continuous Audio Language Models Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy codecs with a limited bitrate. As a consequence, increasing audio quality requires generating more tokens, which imposes a trade-off between fidelity and computational cost. We address this issue by studying Continuous Audio Language Models (CALM). These models instantiate a large Transformer backbone that produces a contextual embedding at every timestep. This sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling. By avoiding lossy compression, CALM achieves higher quality at lower computational cost than their discrete counterpart. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. Samples are available at https://continuous-audio-language-models.github.io 5 authors · Published on Sep 8, 2025 Upvote 11 GitHub 7.35k arXiv Page Continuous Audio Language Models Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy codecs with a limited bitrate. As a consequence, increasing audio quality requires generating more tokens, which imposes a trade-off between fidelity and computational cost. We address this issue by studying Continuous Audio Language Models (CALM). These models instantiate a large Transformer backbone that produces a contextual embedding at every timestep. This sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling. By avoiding lossy compression, CALM achieves higher quality at lower computational cost than their discrete counterpart. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. Samples are available at https://continuous-audio-language-models.github.io 5 authors · Sep 8, 2025 Upvote 11 GitHub 7.35k arXiv Page TradingAgents: Multi-Agents LLM Financial Trading Framework A multi-agent framework using large language models for stock trading simulates real-world trading firms, improving performance metrics like cumulative returns and Sharpe ratio. 4 authors · Published on Dec 28, 2024 Upvote 110 GitHub 92.3k arXiv Page TradingAgents: Multi-Agents LLM Financial Trading Framework A multi-agent framework using large language models for stock trading simulates real-world trading firms, improving performance metrics like cumulative returns and Sharpe ratio. 4 authors · Dec 28, 2024 Upvote 110 GitHub 92.3k arXiv Page Submitted by taesiri SkillOpt: Executive Strategy for Self-Evolving Agent Skills SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments. Microsoft Research · Published on May 22, 2026 Upvote 254 GitHub 12.2k arXiv Page Submitted by taesiri SkillOpt: Executive Strategy for Self-Evolving Agent Skills SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments. Microsoft Research · May 22, 2026 Upvote 254 GitHub 12.2k arXiv Page Submitted by cherubicxn Vision Pretraining for Dense Spatial Perception Boundary modeling enables dense spatial perception by learning sub-pixel representations that enhance depth estimation and support embodied AI applications. Robbyant · Published on Jul 6, 2026 Upvote 42 GitHub 631 arXiv Page Submitted by cherubicxn Vision Pretraining for Dense Spatial Perception Boundary modeling enables dense spatial perception by learning sub-pixel representations that enhance depth estimation and support embodied AI applications. Robbyant · Jul 6, 2026 Upvote 42 GitHub 631 arXiv Page Submitted by akhaliq OpenDevin: An Open Platform for AI Software Developers as Generalist Agents OpenDevin is a platform for developing AI agents that interact with the world by writing code, using command lines, and browsing the web, with support for multiple agents and evaluation benchmarks. 24 authors · Published on Jul 23, 2024 Upvote 82 GitHub 80.5k arXiv Page Submitted by akhaliq OpenDevin: An Open Platform for AI Software Developers as Generalist Agents OpenDevin is a platform for developing AI agents that interact with the world by writing code, using command lines, and browsing the web, with support for multiple agents and evaluation benchmarks. 24 authors · Jul 23, 2024 Upvote 82 GitHub 80.5k arXiv Page Submitted by jt-zhang Vidu S1: A Real-Time Interactive Video Generation Model Vidu S1 is a real-time interactive video generation model that supports voice-controlled digital character animation with infinite-length output and high frame rate on consumer hardware. Tsinghua University · Published on Jul 3, 2026 Upvote 116 GitHub 151 arXiv Page Submitted by jt-zhang Vidu S1: A Real-Time Interactive Video Generation Model Vidu S1 is a real-time interactive video generation model that supports voice-controlled digital character animation with infinite-length output and high frame rate on consumer hardware. Tsinghua University · Jul 3, 2026 Upvote 116 GitHub 151 arXiv Page Submitted by taesiri Unlimited OCR Works Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass. BAIDU · Published on Jun 22, 2026 Upvote 54 GitHub 14k arXiv Page Submitted by taesiri Unlimited OCR Works Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass. BAIDU · Jun 22, 2026 Upvote 54 GitHub 14k arXiv Page Submitted by taesiri MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing MinerU2.5, a 1.2B-parameter document parsing vision-language model, achieves state-of-the-art recognition accuracy with computational efficiency through a coarse-to-fine parsing strategy. 61 authors · Published on Sep 26, 2025 Upvote 175 GitHub 74.3k arXiv Page Submitted by taesiri MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing MinerU2.5, a 1.2B-parameter document parsing vision-language model, achieves state-of-the-art recognition accuracy with computational efficiency through a coarse-to-fine parsing strategy. 61 authors · Sep 26, 2025 Upvote 175 GitHub 74.3k arXiv Page Submitted by nielsr Geometric Context Transformer for Streaming 3D Reconstruction LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from video streams using a geometric context transformer architecture with specialized attention mechanisms for coordinate grounding, dense geometric cues, and long-range drift correction, achieving stable real-time performance at 20 FPS. Robbyant · Published on Apr 15, 2026 Upvote 26 GitHub 10.5k arXiv Page Submitted by nielsr Geometric Context Transformer for Streaming 3D Reconstruction LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from video streams using a geometric context transformer architecture with specialized attention mechanisms for coordinate grounding, dense geometric cues, and long-range drift correction, achieving stable real-time performance at 20 FPS. Robbyant · Apr 15, 2026 Upvote 26 GitHub 10.5k arXiv Page Submitted by Weiww99 From Foundation to Application: Improving VLA Models in Practice LingBot-VLA 2.0 enhances generalization across tasks and embodiments through expanded data preprocessing and training on diverse robot configurations, extends action space to include whole-body degrees of freedom for complex manipulation tasks, and incorporates predictive dynamics modeling using video representation and depth estimation for improved temporal reasoning. Robbyant · Published on Jul 7, 2026 Upvote 17 GitHub 441 arXiv Page Submitted by Weiww99 From Foundation to Application: Improving VLA Models in Practice LingBot-VLA 2.0 enhances generalization across tasks and embodiments through expanded data preprocessing and training on diverse robot configurations, extends action space to include whole-body degrees of freedom for complex manipulation tasks, and incorporates predictive dynamics modeling using video representation and depth estimation for improved temporal reasoning. Robbyant · Jul 7, 2026 Upvote 17 GitHub 441 arXiv Page Submitted by akhaliq Efficient Memory Management for Large Language Model Serving with PagedAttention PagedAttention algorithm and vLLM system enhance the throughput of large language models by efficiently managing memory and reducing waste in the key-value cache. 9 authors · Published on Sep 12, 2023 Upvote 61 GitHub 86k arXiv Page Submitted by akhaliq Efficient Memory Management for Large Language Model Serving with PagedAttention PagedAttention algorithm and vLLM system enhance the throughput of large language models by efficiently managing memory and reducing waste in the key-value cache. 9 authors · Sep 12, 2023 Upvote 61 GitHub 86k arXiv Page Submitted by fistyyyy ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes ResearchStudio-Idea provides a skill suite for effective research ideation that combines literature search, novelty checking, and pattern-guided generation to produce traceable research proposals. Microsoft · Published on Jul 5, 2026 Upvote 50 GitHub 473 arXiv Page Submitted by fistyyyy ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes ResearchStudio-Idea provides a skill suite for effective research ideation that combines literature search, novelty checking, and pattern-guided generation to produce traceable research proposals. Microsoft · Jul 5, 2026 Upvote 50 GitHub 473 arXiv Page Submitted by ChengCui PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training PaddleOCR-VL-1.6 enhances document parsing performance through targeted data optimization and progressive post-training techniques, achieving state-of-the-art results on OmniDocBench v1.6. PaddlePaddle · Published on Jun 2, 2026 Upvote 24 GitHub 85.3k arXiv Page Submitted by ChengCui PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training PaddleOCR-VL-1.6 enhances document parsing performance through targeted data optimization and progressive post-training techniques, achieving state-of-the-art results on OmniDocBench v1.6. PaddlePaddle · Jun 2, 2026 Upvote 24 GitHub 85.3k arXiv Page EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning EverMemOS presents a self-organizing memory system for large language models that processes dialogue streams into structured memory cells and scenes to enhance long-term interaction capabilities. 11 authors · Published on Jan 5, 2026 Upvote 14 GitHub 10.8k arXiv Page EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning EverMemOS presents a self-organizing memory system for large language models that processes dialogue streams into structured memory cells and scenes to enhance long-term interaction capabilities. 11 authors · Jan 5, 2026 Upvote 14 GitHub 10.8k arXiv Page Submitted by akhaliq Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency. 5 authors · Published on Apr 28, 2025 Upvote 67 GitHub 60.6k arXiv Page Submitted by akhaliq Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency. 5 authors · Apr 28, 2025 Upvote 67 GitHub 60.6k arXiv Page Submitted by taesiri Multiplayer Interactive World Models with Representation Autoencoders A large-scale multiplayer world model trained on extensive gameplay data demonstrates stable long-horizon rollouts in a complex physics-based environment while maintaining coherence across multiple agents' actions. 27 authors · Published on Jul 6, 2026 Upvote 20 GitHub 355 arXiv Page Submitted by taesiri Multiplayer Interactive World Models with Representation Autoencoders A large-scale multiplayer world model trained on extensive gameplay data demonstrates stable long-horizon rollouts in a complex physics-based environment while maintaining coherence across multiple agents' actions. 27 authors · Jul 6, 2026 Upvote 20 GitHub 355 arXiv Page LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference LMCACHE enables efficient KV cache management for large language models by storing caches outside GPU memory, supporting cache reuse across queries and inference engines while achieving significant throughput improvements. 11 authors · Published on Oct 8, 2025 Upvote 9 GitHub 10.4k arXiv Page LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference LMCACHE enables efficient KV cache management for large language models by storing caches outside GPU memory, supporting cache reuse across queries and inference engines while achieving significant throughput improvements. 11 authors · Oct 8, 2025 Upvote 9 GitHub 10.4k arXiv Page Submitted by taesiri LongCat-Video Technical Report LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention. LongCat · Published on Oct 25, 2025 Upvote 39 GitHub 5.18k arXiv Page Submitted by taesiri LongCat-Video Technical Report LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention. LongCat · Oct 25, 2025 Upvote 39 GitHub 5.18k arXiv Page Submitted by taesiri AlayaWorld: Long-Horizon and Playable Video World Generation AlayaWorld is an open-source framework for creating interactive generative worlds that enables real-time user interaction and supports diverse actions within a modular architecture. 17 authors · Published on Jul 7, 2026 Upvote 83 GitHub 224 arXiv Page Submitted by taesiri AlayaWorld: Long-Horizon and Playable Video World Generation AlayaWorld is an open-source framework for creating interactive generative worlds that enables real-time user interaction and supports diverse actions within a modular architecture. 17 authors · Jul 7, 2026 Upvote 83 GitHub 224 arXiv Page Submitted by TianxingChen RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies RoboDojo presents a unified sim-and-real benchmark for evaluating generalist robot manipulation policies across diverse tasks and evaluation dimensions. RoboDojo-Benchmark · Published on Jul 7, 2026 Upvote 11 GitHub 181 arXiv Page Submitted by TianxingChen RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies RoboDojo presents a unified sim-and-real benchmark for evaluating generalist robot manipulation policies across diverse tasks and evaluation dimensions. RoboDojo-Benchmark · Jul 7, 2026 Upvote 11 GitHub 181 arXiv Page OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation A novel GPT-based model, OmniFlatten, enables real-time natural full-duplex spoken dialogue through a multi-stage post-training technique that integrates speech and text without altering the original model's architecture. 9 authors · Published on Oct 23, 2024 Upvote 16 GitHub 61.1k arXiv Page OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation A novel GPT-based model, OmniFlatten, enables real-time natural full-duplex spoken dialogue through a multi-stage post-training technique that integrates speech and text without altering the original model's architecture. 9 authors · Oct 23, 2024 Upvote 16 GitHub 61.1k arXiv Page Submitted by zbhpku DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI DataFlow is an LLM-driven data preparation framework that enhances data quality and reproducibility for various tasks, improving LLM performance with automatically generated pipelines. Peking University · Published on Dec 18, 2025 Upvote 225 GitHub 6.25k arXiv Page Submitted by zbhpku DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI DataFlow is an LLM-driven data preparation framework that enhances data quality and reproducibility for various tasks, improving LLM performance with automatically generated pipelines. Peking University · Dec 18, 2025 Upvote 225 GitHub 6.25k arXiv Page Submitted by andito SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion SmolDocling is a compact vision-language model that performs end-to-end document conversion with robust performance across various document types using 256M parameters and a new markup format. IBM Granite · Published on Mar 14, 2025 Upvote 164 GitHub 63k arXiv Page Submitted by andito SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion SmolDocling is a compact vision-language model that performs end-to-end document conversion with robust performance across various document types using 256M parameters and a new markup format. IBM Granite · Mar 14, 2025 Upvote 164 GitHub 63k arXiv Page olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models olmOCR is an open-source toolkit using a fine-tuned vision language model to process PDFs into clean text while preserving structure, optimized for large-scale batch processing. Ai2 · Published on Feb 25, 2025 Upvote 13 GitHub 19.1k arXiv Page olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models olmOCR is an open-source toolkit using a fine-tuned vision language model to process PDFs into clean text while preserving structure, optimized for large-scale batch processing. Ai2 · Feb 25, 2025 Upvote 13 GitHub 19.1k arXiv Page Submitted by rubenohana The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning A large-scale dataset collection, The Well, provides diverse numerical simulations for benchmarking machine learning models in physical systems simulation. 26 authors · Published on Nov 30, 2024 Upvote 26 GitHub 3.92k arXiv Page Submitted by rubenohana The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning A large-scale dataset collection, The Well, provides diverse numerical simulations for benchmarking machine learning models in physical systems simulation. 26 authors · Nov 30, 2024 Upvote 26 GitHub 3.92k arXiv Page PyTorch Distributed: Experiences on Accelerating Data Parallel Training The PyTorch distributed data parallel module optimizes large-scale model training using techniques like gradient bucketing, computation-communication overlap, and selective synchronization to achieve near-linear scalability. 11 authors · Published on Jun 28, 2020 Upvote 10 GitHub 102k arXiv Page PyTorch Distributed: Experiences on Accelerating Data Parallel Training The PyTorch distributed data parallel module optimizes large-scale model training using techniques like gradient bucketing, computation-communication overlap, and selective synchronization to achieve near-linear scalability. 11 authors · Jun 28, 2020 Upvote 10 GitHub 102k arXiv Page Submitted by akhaliq Very Large-Scale Multi-Agent Simulation in AgentScope Enhancements to the AgentScope platform improve scalability, efficiency, and ease of use for large-scale multi-agent simulations through distributed mechanisms, flexible environments, and user-friendly tools. 8 authors · Published on Jul 25, 2024 Upvote 44 GitHub 27.8k arXiv Page Submitted by akhaliq Very Large-Scale Multi-Agent Simulation in AgentScope Enhancements to the AgentScope platform improve scalability, efficiency, and ease of use for large-scale multi-agent simulations through distributed mechanisms, flexible environments, and user-friendly tools. 8 authors · Jul 25, 2024 Upvote 44 GitHub 27.8k arXiv Page Submitted by taesiri GLM-5: from Vibe Coding to Agentic Engineering GLM-5 advances foundation models with DSA for cost reduction, asynchronous reinforcement learning for improved alignment, and enhanced coding capabilities for real-world software engineering. 186 authors · Published on Feb 17, 2026 Upvote 196 GitHub 6.47k arXiv Page Submitted by taesiri GLM-5: from Vibe Coding to Agentic Engineering GLM-5 advances foundation models with DSA for cost reduction, asynchronous reinforcement learning for improved alignment, and enhanced coding capabilities for real-world software engineering. 186 authors · Feb 17, 2026 Upvote 196 GitHub 6.47k arXiv Page Kronos: A Foundation Model for the Language of Financial Markets Kronos, a specialized pre-training framework for financial K-line data, outperforms existing models in forecasting and synthetic data generation through a unique tokenizer and autoregressive pre-training on a large dataset. 7 authors · Published on Aug 2, 2025 Upvote 47 GitHub 32.1k arXiv Page Kronos: A Foundation Model for the Language of Financial Markets Kronos, a specialized pre-training framework for financial K-line data, outperforms existing models in forecasting and synthetic data generation through a unique tokenizer and autoregressive pre-training on a large dataset. 7 authors · Aug 2, 2025 Upvote 47 GitHub 32.1k arXiv Page Submitted by taesiri AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications AgentScope enhances agentic applications by providing flexible tool-based interactions, unified interfaces, and advanced infrastructure based on the ReAct paradigm, supporting efficient and safe development and deployment. 23 authors · Published on Aug 22, 2025 Upvote 67 GitHub 27.8k arXiv Page Submitted by taesiri AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications AgentScope enhances agentic applications by providing flexible tool-based interactions, unified interfaces, and advanced infrastructure based on the ReAct paradigm, supporting efficient and safe development and deployment. 23 authors · Aug 22, 2025 Upvote 67 GitHub 27.8k arXiv Page Submitted by RuofengYang ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration ARIS is an open-source research harness that uses cross-model adversarial collaboration to ensure reliable long-term research outcomes through coordinated execution, orchestration, and assurance layers. Shanghai Jiao Tong University · Published on May 4, 2026 Upvote 143 GitHub 13.3k arXiv Page Submitted by RuofengYang ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration ARIS is an open-source research harness that uses cross-model adversarial collaboration to ensure reliable long-term research outcomes through coordinated execution, orchestration, and assurance layers. Shanghai Jiao Tong University · May 4, 2026 Upvote 143 GitHub 13.3k arXiv Page Submitted by Jeff-Wang GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation World models for robotic policy evaluation are systematically studied through a new benchmark, revealing that long-horizon rollout consistency and robot-specific controllability are more important than short-term visual realism for reliable policy assessment. GigaAI · Published on Jul 2, 2026 Upvote 37 GitHub 303 arXiv Page Submitted by Jeff-Wang GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation World models for robotic policy evaluation are systematically studied through a new benchmark, revealing that long-horizon rollout consistency and robot-specific controllability are more important than short-term visual realism for reliable policy assessment. GigaAI · Jul 2, 2026 Upvote 37 GitHub 303 arXiv Page A decoder-only foundation model for time-series forecasting A large language model adapted for time-series forecasting achieves near-optimal zero-shot performance on diverse datasets across different time scales and granularities. 4 authors · Published on Oct 14, 2023 Upvote 37 GitHub 26.7k arXiv Page A decoder-only foundation model for time-series forecasting A large language model adapted for time-series forecasting achieves near-optimal zero-shot performance on diverse datasets across different time scales and granularities. 4 authors · Oct 14, 2023 Upvote 37 GitHub 26.7k arXiv Page Zep: A Temporal Knowledge Graph Architecture for Agent Memory Zep, a memory layer service, outperforms MemGPT in the DMR benchmark and LongMemEval by excelling in dynamic knowledge integration and temporal reasoning, critical for enterprise use cases. 5 authors · Published on Jan 20, 2025 Upvote 15 GitHub 28.6k arXiv Page Zep: A Temporal Knowledge Graph Architecture for Agent Memory Zep, a memory layer service, outperforms MemGPT in the DMR benchmark and LongMemEval by excelling in dynamic knowledge integration and temporal reasoning, critical for enterprise use cases. 5 authors · Jan 20, 2025 Upvote 15 GitHub 28.6k arXiv Page Submitted by nielsr Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models YOLO26 addresses real-time vision challenges through a unified model family with NMS-free inference, improved training strategies, and multi-task capabilities spanning detection, segmentation, and pose estimation. Ultralytics · Published on Jun 2, 2026 Upvote 18 GitHub 59.4k arXiv Page Submitted by nielsr Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models YOLO26 addresses real-time vision challenges through a unified model family with NMS-free inference, improved training strategies, and multi-task capabilities spanning detection, segmentation, and pose estimation. Ultralytics · Jun 2, 2026 Upvote 18 GitHub 59.4k arXiv Page LightRAG: Simple and Fast Retrieval-Augmented Generation LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times. 5 authors · Published on Oct 8, 2024 Upvote 41 GitHub 37.6k arXiv Page LightRAG: Simple and Fast Retrieval-Augmented Generation LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times. 5 authors · Oct 8, 2024 Upvote 41 GitHub 37.6k arXiv Page Submitted by taesiri PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space PixWorld presents a unified pixel-space diffusion approach for 3D reconstruction and generation that overcomes limitations of latent-space methods through direct image-level supervision and geometry-aware feature alignment. Nanyang Technological University · Published on Jul 6, 2026 Upvote 61 GitHub 139 arXiv Page Submitted by taesiri PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space PixWorld presents a unified pixel-space diffusion approach for 3D reconstruction and generation that overcomes limitations of latent-space methods through direct image-level supervision and geometry-aware feature alignment. Nanyang Technological University · Jul 6, 2026 Upvote 61 GitHub 139 arXiv Page AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets AI-Trader presents the first fully automated live benchmark for evaluating large language models in financial decision-making across multiple markets with autonomous information processing. 6 authors · Published on Dec 1, 2025 Upvote 12 GitHub 20.7k arXiv Page AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets AI-Trader presents the first fully automated live benchmark for evaluating large language models in financial decision-making across multiple markets with autonomous information processing. 6 authors · Dec 1, 2025 Upvote 12 GitHub 20.7k arXiv Page Multi-module GRPO: Composing Policy Gradients and Prompt Optimization for Language Model Programs mmGRPO, a multi-module extension of GRPO, enhances accuracy in modular AI systems by optimizing LM calls and prompts across various tasks. 13 authors · Published on Aug 6, 2025 Upvote 6 GitHub 36k arXiv Page Multi-module GRPO: Composing Policy Gradients and Prompt Optimization for Language Model Programs mmGRPO, a multi-module extension of GRPO, enhances accuracy in modular AI systems by optimizing LM calls and prompts across various tasks. 13 authors · Aug 6, 2025 Upvote 6 GitHub 36k arXiv Page Submitted by yshenaw SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe A minimal viable pipeline for skill optimization is proposed through Zeroth-Order optimization formalization, eliminating redundancies while maintaining convergence and generalization through trajectory exploration, consensus mining, and validation gating principles. LMMs-Lab · Published on Jul 3, 2026 Upvote 25 GitHub 76 arXiv Page Submitted by yshenaw SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe A minimal viable pipeline for skill optimization is proposed through Zeroth-Order optimization formalization, eliminating redundancies while maintaining convergence and generalization through trajectory exploration, consensus mining, and validation gating principles. LMMs-Lab · Jul 3, 2026 Upvote 25 GitHub 76 arXiv Page Submitted by huohua325 MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision MemSlides presents a hierarchical memory framework for personalized presentation agents that separates long-term user profiles, working memory for session constraints, and tool memory for reusable execution experiences to enable stable personalization and reliable local edits across multi-turn revisions. 4 authors · Published on Jun 15, 2026 Upvote 176 GitHub 658 arXiv Page Submitted by huohua325 MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision MemSlides presents a hierarchical memory framework for personalized presentation agents that separates long-term user profiles, working memory for session constraints, and tool memory for reusable execution experiences to enable stable personalization and reliable local edits across multi-turn revisions. 4 authors · Jun 15, 2026 Upvote 176 GitHub 658 arXiv Page Submitted by akhaliq LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models LlamaFactory is a unified framework enabling efficient fine-tuning of large language models across various tasks using a web-based user interface. 5 authors · Published on Mar 20, 2024 Upvote 186 GitHub 73.2k arXiv Page Submitted by akhaliq LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models LlamaFactory is a unified framework enabling efficient fine-tuning of large language models across various tasks using a web-based user interface. 5 authors · Mar 20, 2024 Upvote 186 GitHub 73.2k arXiv Page Submitted by shanyou92 Kairos: A Native World Model Stack for Physical AI Kairos is a world model framework that learns from diverse experiences, maintains persistent states through hybrid temporal attention mechanisms, and operates efficiently across different hardware platforms for physical AI applications. 24 authors · Published on Jun 16, 2026 Upvote 38 GitHub 1.48k arXiv Page Submitted by shanyou92 Kairos: A Native World Model Stack for Physical AI Kairos is a world model framework that learns from diverse experiences, maintains persistent states through hybrid temporal attention mechanisms, and operates efficiently across different hardware platforms for physical AI applications. 24 authors · Jun 16, 2026 Upvote 38 GitHub 1.48k arXiv Page Submitted by shixuanke Vision as Unified Multimodal Generation A unified multimodal model formulates computer vision tasks as generation problems using natural language and visual prompts, achieving performance comparable to specialized systems across diverse vision tasks. SenseNova · Published on Jul 7, 2026 Upvote 44 GitHub 101 arXiv Page Submitted by shixuanke Vision as Unified Multimodal Generation A unified multimodal model formulates computer vision tasks as generation problems using natural language and visual prompts, achieving performance comparable to specialized systems across diverse vision tasks. SenseNova · Jul 7, 2026 Upvote 44 GitHub 101 arXiv Page Submitted by iieycx JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence A vision-language model operates continuously in real-time, making autonomous decisions about when to respond or delegate, enabling interactive systems that perceive and act upon environmental changes without user prompting. JD.com Open Source · Published on Jun 10, 2026 Upvote 210 GitHub 1.23k arXiv Page Submitted by iieycx JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence A vision-language model operates continuously in real-time, making autonomous decisions about when to respond or delegate, enabling interactive systems that perceive and act upon environmental changes without user prompting. JD.com Open Source · Jun 10, 2026 Upvote 210 GitHub 1.23k arXiv Page Submitted by Rbin RAG-Anything: All-in-One RAG Framework RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks. Data Intelligence Lab@HKU · Published on Oct 14, 2025 Upvote 83 GitHub 22.1k arXiv Page Submitted by Rbin RAG-Anything: All-in-One RAG Framework RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks. Data Intelligence Lab@HKU · Oct 14, 2025 Upvote 83 GitHub 22.1k arXiv Page Submitted by jbarrow CommonForms: A Large, Diverse Dataset for Form Field Detection A web-scale dataset and models for form field detection are introduced, achieving high precision and supporting diverse languages and domains. 1 authors · Published on Sep 20, 2025 Upvote 22 GitHub 1.11k arXiv Page Submitted by jbarrow CommonForms: A Large, Diverse Dataset for Form Field Detection A web-scale dataset and models for form field detection are introduced, achieving high precision and supporting diverse languages and domains. 1 authors · Sep 20, 2025 Upvote 22 GitHub 1.11k arXiv Page System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs

Trending Papers - Hugging Face Source: Trending Papers - Hugging Face Hugging Face Models Datasets Spaces Buckets new Docs Enterprise Pricing Website Tasks HuggingChat Collections Languages Organizations Community Blog Posts Daily Papers Hardware Learn Discord Forum GitHub Solutions Team & Enterprise Hugging Face PRO Enterprise Support Inference Providers Inference Endpoints Storage Buckets Log In Sign Up new Get trending papers in your email inbox once a day! Get trending papers in your email inbox! Subscribe Trending Papers by AK and the research community Daily Weekly Monthly Trending Papers Submitted by taesiri Infinite Worlds with Versatile Interactions An advanced world modeling system with extended interaction capabilities, real-time processing, diverse interactive elements, and multi-agent behavior control for collaborative virtual environments. Robbyant · Published on Jul 8,… Ứng dụng: nối nghiên cứu với ai, USD, lãi suất và risk regime — đưa vào journal và playbook. DOI/OA chỉ là rail tham chiếu; nội dung chính là summary, takeaways và ứng dụng thị trường.