数据来源：HuggingFace Papers Latest Papers1. QeRL: Beyond Efficiency — Quantization-enhanced Reinforcement Learning for LLMsWe propose QeRL, a Quantization-enhanced Reinforcement Learning framework for large language models (LLMs). While RL is essential for LLMs’ reasoning capabilities, it is resource-intensive, requiring substantial GPU memory and long rollout durations. QeRL addresses these issues by combining NVFP4 quantization with Low-Rank Adaptation (LoRA), accelerating rollout phase of RL wh ...

数据来源：HuggingFace Papers Latest Papers1. Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language FoundationWe introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling l ...

数据来源：HuggingFace Papers Latest Papers1. Grounding Computer Use Agents on Human DemonstrationsBuilding reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements. While large datasets exist for web and mobile interactions, high-quality resources for desktop environments are limited. To address this gap, we introduce GroundCUA, a large-scale desktop grounding dataset built from expert human demonstrations. It covers 87 a ...

数据来源：HuggingFace Papers Latest Papers1. Lumine: An Open Recipe for Building Generalist Agents in 3D Open WorldsWe introduce Lumine, the first open recipe for developing generalist agents capable of completing hours-long complex missions in real time within challenging 3D open-world environments. Lumine adopts a human-like interaction paradigm that unifies perception, reasoning, and action in an end-to-end manner, powered by a vision-language model. It processes raw pixels at 5 Hz to produce pr ...

数据来源：HuggingFace Papers Latest Papers1. One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion ModelsDiffusion models struggle to scale beyond their training resolutions, as direct high-resolution sampling is slow and costly, while post-hoc image super-resolution (ISR) introduces artifacts and additional latency by operating after decoding. We present the Latent Upscaler Adapter (LUA), a lightweight module that performs super-resolution directly on ...

数据来源：HuggingFace Papers Latest Papers1. One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion ModelsDiffusion models struggle to scale beyond their training resolutions, as direct high-resolution sampling is slow and costly, while post-hoc image super-resolution (ISR) introduces artifacts and additional latency by operating after decoding. We present the Latent Upscaler Adapter (LUA), a lightweight module that performs super-resolution directly on ...

数据来源：HuggingFace Papers Latest Papers1. One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion ModelsDiffusion models struggle to scale beyond their training resolutions, as direct high-resolution sampling is slow and costly, while post-hoc image super-resolution (ISR) introduces artifacts and additional latency by operating after decoding. We present the Latent Upscaler Adapter (LUA), a lightweight module that performs super-resolution directly on ...

数据来源：HuggingFace Papers Latest Papers1. DoPE: Denoising Rotary Position EmbeddingRotary Position Embedding (RoPE) in Transformer models has inherent limits that weaken length extrapolation. We reinterpret the attention map with positional encoding as a noisy feature map, and propose Denoising Positional Encoding (DoPE), a training-free method based on truncated matrix entropy to detect outlier frequency bands in the feature map. Leveraging the noise characteristics of the feature map, we furth ...

数据来源：HuggingFace Papers Latest Papers1. P1: Mastering Physics Olympiads with Reinforcement LearningRecent progress in large language models (LLMs) has moved the frontier from puzzle-solving to science-grade reasoning-the kind needed to tackle problems whose answers must stand against nature, not merely fit a rubric. Physics is the sharpest test of this shift, which binds symbols to reality in a fundamental way, serving as the cornerstone of most modern technologies. In this work, we manage to ...

数据来源：HuggingFace Papers Latest Papers1. AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language ModelsWe present AraLingBench: a fully human annotated benchmark for evaluating the Arabic linguistic competence of large language models (LLMs). The benchmark spans five core categories: grammar, morphology, spelling, reading comprehension, and syntax, through 150 expert-designed multiple choice questions that directly assess structural language unde ...

数据来源：HuggingFace Papers Latest Papers1. V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation ModelsRecent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video reasoning across four key dimensions: structured problem-solving, spatial cognition, pattern-based inference, and physical dynamics. Th ...

数据来源：HuggingFace Papers Latest Papers1. Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated ReasoningLarge Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an alternative but are typically restricted by the model’s inherent capabilities and single-round interactions, hindering the development ...

数据来源：HuggingFace Papers Latest Papers1. OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General RecipeRecent advancements in large reasoning models have fueled growing interest in extending such capabilities to multimodal domains. However, despite notable progress in visual reasoning, the lack of transparent and reproducible data curation and training strategies remains a major barrier to scalable research. In this work, we introduce OpenMMReasoner, a fully tran ...

数据来源：HuggingFace Papers Latest Papers1. Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated ReasoningLarge Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an alternative but are typically restricted by the model’s inherent capabilities and single-round interactions, hindering the development ...

数据来源：HuggingFace Papers Latest Papers1. GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution AlgorithmsRecent advances in LLM-guided evolutionary computation, particularly AlphaEvolve (Novikov et al., 2025; Georgiev et al., 2025), have demonstrated remarkable success in discovering novel mathematical constructions and solving challenging optimization problems. However, the high-level descriptions in published work leave many implementation details unspecified, hindering ...