Related papers: Data Kernel Perspective Space Performance Guarante…

Data plays a fundamental role in consolidating markets, services, and products in the digital financial ecosystem. However, the use of real data, especially in the financial context, can lead to privacy risks and access restrictions,…

The usefulness of Large Language Models (LLM) is being continuously tested in various fields. However, their intrinsic linguistic characteristic is still one of the limiting factors when applying these models to exact sciences. In this…

The programming capabilities of large language models (LLMs) have revolutionized automatic code generation and opened new avenues for automatic statistical analysis. However, the validity and quality of these generated codes need to be…

Large-scale pre-trained language models have achieved impressive results on a wide range of downstream tasks recently. However, fine-tuning an extremely large-scale pre-trained language model on limited target datasets is often plagued by…

Performance modeling, a pivotal domain in program cost analysis, currently relies on manually crafted models constrained by various program and hardware limitations, especially in the intricate landscape of GPGPU. Meanwhile, Large Language…

Many important problems in science and engineering, such as drug design, involve optimizing an expensive black-box objective function over a complex, high-dimensional, and structured input space. Although machine learning techniques have…

As deep learning-based, data-driven information extraction systems become increasingly integrated into modern document processing workflows, one primary concern is the risk of malicious leakage of sensitive private data from these systems.…

Empirical data can often be considered as samples from a set of probability distributions. Kernel methods have emerged as a natural approach for learning to classify these distributions. Although numerous kernels between distributions have…

The integration of privacy measures, including differential privacy techniques, ensures a provable privacy guarantee for the synthetic data. However, challenges arise for Generative Deep Learning models when tasked with generating realistic…

Using Large Language Models (LLMs) to generate synthetic data for model training has become increasingly popular in recent years. While LLMs are capable of producing realistic training data, the effectiveness of data generation is…

Model collapse in synthetic data indicates that iterative training on self-generated data leads to a gradual decline in performance. With the proliferation of AI models, synthetic data will fundamentally reshape the web data ecosystem.…

Large language models are increasingly applied to materials science, yet fundamental questions remain about their reliability and knowledge encoding. Evaluating 25 LLMs across four materials science tasks -- over 200 base and fine-tuned…

The advent of Large Language Models (LLMs) has significantly advanced the field of automated code generation. LLMs rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages. For low-resource…

Mathematical reasoning remains challenging for LLMs due to complex logic and the need for precise computation. Existing methods enhance LLM reasoning by synthesizing datasets through problem rephrasing, but face issues with generation…

Latent space is rapidly emerging as a native substrate for language-based models. While modern systems are still commonly understood through explicit token-level generation, an increasing body of work shows that many critical internal…

Synthetic data has the potential to improve the performance, training efficiency, and privacy of real training examples. Nevertheless, existing approaches for synthetic text generation are mostly heuristics and cannot generate…

The grand goal of AI research, and particularly Self Supervised Learning (SSL), is to produce systems that can successfully solve any possible task. In contrast, current evaluation methods available to AI researchers typically rely on a…

The goal of program synthesis is to automatically generate programs in a particular language from corresponding specifications, e.g. input-output behavior. Many current approaches achieve impressive results after training on randomly…

Optimizing scientific software is a difficult task because codebases are often large and complex, and performance can depend upon several factors including the algorithm, its implementation, and hardware among others. Causes of poor…

LLM inference is still evaluated mainly as a model or software problem: accuracy, latency, throughput, and hardware utilization. This is incomplete. At deployment scale, the relevant output is a quality-conditioned token produced under…