arXiv 论文速递

系统重审像素空间扩散Transformer的设计空间，挑战潜空间扩散的默认范式，对生成模型架构选择有重要指导意义。

Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the lossy latent bottleneck and separately trained autoencoder. JiT …

揭示微调引发的非目标行为耦合现象及其形成机制，对LLM对齐与安全微调的风险评估至关重要。

Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more sycophantic, a…

Reproducible and analytically robust research findings are essential to scientific progress, but evaluating these properties typically requires costly manual effort. We investigate…

Parameterized quantum circuits are widely investigated in quantum machine learning, yet how their architecture can provide task-aligned inductive biases remains poorly understood. …

指出正确推理轨迹未必适合特定学生，提出以学生为条件的轨迹构建方法，提升推理蒸馏的有效性。

A reasoning trace can accompany a correct answer without providing effective supervision for a particular student. We study how to construct traces that improve learning beyond ans…

A planner with a fixed budget of preventive help must decide whom to help and when. Waiting reveals risk but removes intervention opportunities as higher-risk individuals leave fir…

Future quantum networks will rely on control-plane decisions such as routing, scheduling, entanglement provisioning, purification, and memory allocation. Each decision depends on a…

提出AI智能体自主构建自驱动实验室的框架，将自动化科研从执行推进到实验平台自建，意义重大。

Self-driving laboratories (SDLs) accelerate scientific discovery by automating experimental execution and optimization. AI agents can increasingly propose new experiments, but exis…

The evidence, $\mathcal{Z} = p(x | \mathcal{M})$, of a data-generating model $\mathcal{M}$ is a powerful tool in Bayesian frameworks: it enables model inference, model misspecifica…

提出球面SO(3)等变卷积网络，无需重新学习物理对称性，对球面科学数据的等变建模有广泛价值。

Many of the most important datasets in the physical sciences live natively on the sphere, and these data often carry no preferred position or orientation. Using methods that do not…

Designing RNA sequences that reliably fold into specific secondary structures is essential for understanding their biological functions but remains a challenging computational prob…

Long-term memory enables language-model agents to personalize future interactions, but a finite memory bank cannot preserve every extracted fact. Existing memory gating policies ar…