数据来源：github.com/trending global Languagesthedotmack/claude-memA Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude’s agent-sdk), and injects relevant context back into future sessions. ⭐ Stars: 18057 🍴 Forks: 0 📝 Language: TypeScript ThePrimeagen/99Neovim AI agent done right ⭐ Stars: 3031 🍴 Forks: 0 📝 Language: Lua termux/termux-appTermux - a terminal emulator application for Android OS extendible by ...

数据来源：github.com/trending global Languagesthedotmack/claude-memA Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude’s agent-sdk), and injects relevant context back into future sessions. ⭐ Stars: 20187 🍴 Forks: 0 📝 Language: TypeScript masoncl/review-promptsAI review prompts ⭐ Stars: 326 🍴 Forks: 0 📝 Language: Python openai/skillsSkills Catalog for Codex ⭐ Stars: 2989 🍴 Forks: 0 📝 Language: Python ...

数据来源：github.com/trending global Languagesthedotmack/claude-memA Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude’s agent-sdk), and injects relevant context back into future sessions. ⭐ Stars: 22448 🍴 Forks: 0 📝 Language: TypeScript openai/skillsSkills Catalog for Codex ⭐ Stars: 3644 🍴 Forks: 0 📝 Language: Python disler/claude-code-hooks-masteryMaster Claude Code Hooks ⭐ Stars: 2350 🍴 Forks: 0 📝 L ...

数据来源：HuggingFace Papers Latest Papers1. SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human GenerationThe rapid development of large-scale models has catalyzed significant breakthroughs in the digital human domain. These advanced methodologies offer high-fidelity solutions for avatar driving and rendering, leading academia to focus on the next major challenge: audio-visual dyadic interactive virtual human. To facilitate research in this emerging area, we ...

数据来源：HuggingFace Papers Latest Papers1. Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data ContaminationThe reasoning capabilities of large language models (LLMs) have been a longstanding focus of research. Recent works have further enhanced these capabilities using reinforcement learning (RL), with many new methods claiming significant improvements with minimal or no external supervision. Surprisingly, some studies even suggest that random or incorrect reward ...

数据来源：HuggingFace Papers Latest Papers1. Test-Time Scaling with Reflective Generative ModelWe introduce our first reflective generative model MetaStone-S1, which obtains OpenAI o3-mini’s performance via the new Reflective Generative Form. The new form focuses on high-quality reasoning trajectory selection and contains two novelties: 1) A unified interface for policy and process reward model: we share the backbone network and use task-specific heads for reasoning trajectory predicting and scorin ...

数据来源：HuggingFace Papers Latest Papers1. Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMsRetrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts. This survey synthesizes both strands under a unified reasoning-retrieval perspective. We first map h ...

数据来源：HuggingFace Papers Latest Papers1. A Survey of Context Engineering for Large Language ModelsThe performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to encompass the systematic optimization of information payloads for LLMs. We present a comprehensive taxonomy decomposing Context Engineering into its foundational co ...

数据来源：HuggingFace Papers Latest Papers1. A Survey of Context Engineering for Large Language ModelsThe performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to encompass the systematic optimization of information payloads for LLMs. We present a comprehensive taxonomy decomposing Context Engineering into its foundational co ...

数据来源：HuggingFace Papers Latest Papers1. A Survey of Context Engineering for Large Language ModelsThe performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to encompass the systematic optimization of information payloads for LLMs. We present a comprehensive taxonomy decomposing Context Engineering into its foundational co ...

数据来源：HuggingFace Papers Latest Papers1. A Data-Centric Framework for Addressing Phonetic and Prosodic Challenges in Russian Speech Generative ModelsRussian speech synthesis presents distinctive challenges, including vowel reduction, consonant devoicing, variable stress patterns, homograph ambiguity, and unnatural intonation. This paper introduces Balalaika, a novel dataset comprising more than 2,000 hours of studio-quality Russian speech with comprehensive textual annotations, including punctu ...

数据来源：HuggingFace Papers Latest Papers1. HOComp: Interaction-Aware Human-Object CompositionWhile existing image-guided composition methods may help insert a foreground object onto a user-specified region of a background image, achieving natural blending inside the region with the rest of the image unchanged, we observe that these existing methods often struggle in synthesizing seamless interaction-aware compositions when the task involves human-object interactions. In this paper, we first propo ...

数据来源：HuggingFace Papers Latest Papers1. A Survey of Context Engineering for Large Language ModelsThe performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a formal discipline that transcends simple prompt design to encompass the systematic optimization of information payloads for LLMs. We present a comprehensive taxonomy decomposing Context Engineering into its foundational co ...

数据来源：HuggingFace Papers Latest Papers1. nablaNABLA: Neighborhood Adaptive Block-Level AttentionRecent progress in transformer-based architectures has demonstrated remarkable success in video generation tasks. However, the quadratic complexity of full attention mechanisms remains a critical bottleneck, particularly for high-resolution and long-duration video sequences. In this paper, we propose NABLA, a novel Neighborhood Adaptive Block-Level Attention mechanism that dynamically adapts to spars ...

数据来源：HuggingFace Papers Latest Papers1. nablaNABLA: Neighborhood Adaptive Block-Level AttentionRecent progress in transformer-based architectures has demonstrated remarkable success in video generation tasks. However, the quadratic complexity of full attention mechanisms remains a critical bottleneck, particularly for high-resolution and long-duration video sequences. In this paper, we propose NABLA, a novel Neighborhood Adaptive Block-Level Attention mechanism that dynamically adapts to spars ...