arXiv 论文速递

3D Gaussian avatars support fast rendering, however, their real-time animation is often challenged by the costly neural inference. We address this bottleneck and show that the anim…

填补LLM网络安全工具调用评测空白，构建Kali Linux细粒度基准与免运行验证奖励，为安全智能体能力评估提供标准。

LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowle…

针对具身智能体技能开发依赖大量人工的问题，提出引导式自我改进框架，降低机器人能力构建成本，推动自主技能学习。

Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control. W…

揭示扩散Transformer中条件嵌入在去噪各步被重复使用的问题，提出嵌入预测改进图像生成，为扩散模型条件机制提供新思路。

In diffusion transformers, a class label or a text prompt is embedded once, and the same condition is reused at every denoising step. We ask whether predicted embeddings can serve …

What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prior idea, buried in an ever-gr…

High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective…

证明多模态模型具备强推理能力，提出视觉化框架释放其跨任务潜力，为多模态智能体的交互式推理提供通用方案。

We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments.…

Full-parameter fine-tuning of large language models (LLMs) incurs substantial optimizer state memory overhead, limiting the model sizes that fit on modern GPUs. Existing approaches…

Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using action gradients of a learned critic. However, critics are typically…

The generalized Schrödinger bridge on a graph moves mass between two distributions while charging a cost for the states visited. It has been approached by learning the rates of a c…

针对离散扩散语言模型表达受限问题，提出分层连续扩散框架，兼顾双向推理与生成质量，推动非自回归语言建模发展。

Discrete diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bidirectional reasoning and global constraint satisfaction. Yet t…

While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical un…