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…

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

提出引导式自改进方法，减少具身智能体技能开发与奖励设计的人力成本，提升跨任务机器人能力的可扩展性。

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

指出扩散Transformer中条件嵌入被重复使用的问题，提出嵌入预测机制，为图像生成引入新的条件利用范式，可能改进生成质量与效率。

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…

提出视觉化推理框架，释放多模态模型在交互环境中的推理潜力，推动多模态智能体在复杂任务上的应用。

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在双向推理上的局限，提出分层连续扩散框架，为语言生成提供替代自回归的新路径，具方法论意义。

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

系统诊断LLM数学推理缺失的基础能力并给出修复方案，对理解与提升大模型推理可靠性有重要价值。

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