相关论文: Bridging the Domain Gap in Equation Distillation w…

Discovering interpretable mathematical equations from observed data (a.k.a. equation discovery or symbolic regression) is a cornerstone of scientific discovery, enabling transparent modeling of physical, biological, and economic systems.…

Large language models (LLMs) often exhibit limited performance on domain-specific tasks due to the natural disproportionate representation of specialized information in their training data and the static nature of these datasets. Knowledge…

High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory and copyright constraints. This scarcity hampers model development--ironically, in…

Foundation models contain a wealth of information from their vast number of training samples. However, most prior arts fail to extract this information in a precise and efficient way for small sample sizes. In this work, we propose a…

Deep generative models can help with data scarcity and privacy by producing synthetic training data, but they struggle in low-data, imbalanced tabular settings to fully learn the complex data distribution. We argue that striving for the…

Recommendation model performance is intrinsically tied to the quality, volume, and relevance of their training data. To address common challenges like data sparsity and cold start, recent researchs have leveraged data from multiple…

Materials design aims to discover novel compounds with desired properties. However, prevailing strategies face critical trade-offs. Conventional element-substitution approaches readily and adaptively incorporate various domain knowledge but…

Discovering functional crystalline materials entails navigating an immense combinatorial design space. While recent advances in generative artificial intelligence have enabled the sampling of chemically plausible compositions and…

Data mixing strategies have successfully reduced the costs involved in training language models. While promising, such methods suffer from two flaws. First, they rely on predetermined data domains (e.g., data sources, task types), which may…

Natural question generation (QG) aims to generate questions from a passage and an answer. Previous works on QG either (i) ignore the rich structure information hidden in text, (ii) solely rely on cross-entropy loss that leads to issues like…

Retrosynthesis is a problem to infer reactant compounds to synthesize a given product compound through chemical reactions. Recent studies on retrosynthesis focus on proposing more sophisticated prediction models, but the dataset to feed the…

Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further training on in-domain data rapidly weakens the model's ability to…

Deciphering how DNA sequence encodes gene regulation remains a central challenge in biology. Advances in machine learning and functional genomics have enabled sequence-to-function (seq2func) models that predict molecular regulatory readouts…

Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains requiring precise information extraction from complex documents. Current evaluation methodologies relying on document-level…

The size and quality of chemical libraries to the drug discovery pipeline are crucial for developing new drugs or repurposing existing drugs. Existing techniques such as combinatorial organic synthesis and High-Throughput Screening usually…

Entity Matching (EM)--the task of determining whether two data records refer to the same real-world entity--is a core task in data integration. Recent advances in deep learning have set a new standard for EM, particularly through…

Retrieval-Augmented Generation (RAG) enhances LLM factuality, but multi-domain applications face challenges like lack of diverse benchmarks and poor out-of-domain generalization. The first contribution of this work is to introduce a diverse…

Distribution shift presents a significant challenge in machine learning, where models often underperform during the test stage when faced with a different distribution than the one they were trained on. This paper focuses on domain shifts,…

Dataset distillation aims to distill the knowledge of a large-scale real dataset into small yet informative synthetic data such that a model trained on it performs as well as a model trained on the full dataset. Despite recent progress,…

In this paper, we aim to adapt a model at test-time using a few unlabeled data to address distribution shifts. To tackle the challenges of extracting domain knowledge from a limited amount of data, it is crucial to utilize correlated…