计算机科学

Untargeted tandem mass spectrometry (MS/MS) detects thousands of small molecules per biological sample, yet most go unidentified because they are absent from spectral libraries. These uncharacterized metabolites and natural products are…

Facial skin dynamics are inherently challenging to simulate due to a combination of geometric, material, and anatomical complexities. Human skin is a nonlinear layered material with spatially heterogeneous attachments to the underlying…

We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories. Fully online OPD is costly because…

Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Distillation (TOP-D), which transforms the notoriously unstable, high-variance On-Policy Distillation (OPD) into a stable…

We propose several approaches for bounding the minim\-um distances of the family of quasi-cyclic LDPC codes in the 5G NR standard. In particular, we show that the high-rate [9984, 8448] and the low-rate [25344, 8448] BG1 5G LDPC codes have…

Reinforcement learning holds significant potential for training large language models (LLMs) to handle multi-turn interactive tasks. However, in long-horizon, multi-turn tasks characterized by sparse outcome rewards, directly training with…

Modern machine learning systems demand extensive datasets for visual recognition. Conversely, humans learn with high efficiency despite severe data limitations, often by acquiring broad categorical structures before refining finer…

The rapid proliferation of Internet of things (IoT) devices has significantly expanded the cyber-attack surface, necessitating robust and privacy-preserving intrusion detection systems (IDS). However, centralized learning approaches often…

Synthesis planning aiming to find pathways of reactions for a target molecule is one of the most important and challenging tasks in drug discovery. Recent progress has produced both specialized deep-learning retrosynthesis systems and…

In their 2018 paper, Agotnes, van Ditmarsch, and Wang extended the notions of success and self-refutation in public announcements to true lies, impossible lies, and $\sigma$-validity in general, where $\sigma$ is a finite or infinite…

Grain growth is governed by the reduction in grain boundary energy and exhibits well-established statistical scaling laws. Developing data-driven surrogates that preserve these physical invariants while remaining computationally scalable…

As autonomous vehicles progress toward fully driverless mobility, a critical question emerges: who understands and responds to passengers when the human driver is absent? Existing autonomous driving systems primarily optimize predefined…

Depression screening from large-scale behavioral data is challenged by fragmented circadian indicators, limited interpretability, and the lack of intervention-oriented analysis. Existing approaches typically analyze sleep, activity, and…

Persona-Trained Monte Carlo (PTMC) estimates distributions of market-outcome functionals by repeatedly simulating limit-order-book interaction among $K$ neural policy bots whose behavioral personas are drawn from a learned heterogeneity…

Graphic design editing requires precise manipulation of typography, layout, and visual hierarchy under strict design constraints. Following the introduction of large language models, organizations have increasingly promoted vision-language…

Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing token compression methods reduce this cost,…

Graph eXplainable AI (G-XAI) is increasingly important for making Graph Neural Networks interpretable and accountable. While a growing number of explainers are available, choosing the right method and assessing the trustworthiness of its…

In this paper, we study the universal approximation property of residual neural networks, and obtain some new results. For input and output dimensions $d_x$ and $d_y$, and LeakyReLU, ReLU, ReLU-like activation functions, the upper and lower…

Most classification problems assume the classes are roughly separable, so that an individual sample can usually be assigned to one class. Single-cell perturbation data violates this assumption: two perturbations can produce different…

Linear Gaussian Bayesian networks, equivalently linear Gaussian structural equation models, recur across statistics, control, and communications; in the vector-valued setting that motivates this work, their nodes are vectors and their edges…