Hai Li

Fine-grained Out-of-Distribution Detection with Mixup Outlier Exposure.

2021 · arXiv (Cornell University)

Enabling out-of-distribution (OOD) detection for DNNs is critical for their safe and reliable operation in the open world. Unfortunately, current works in both methodology and evaluation focus on rather contrived detection problems, and only consider …

Quantum information scrambling in non-Markovian open quantum systems

2022 · arXiv (Cornell University)

In this paper we investigate the dynamics of a spin chain whose two end spins interact with two independent non-Markovian baths by using the non-Markovian quantum state diffusion (QSD) equation approach. Specifically two issues about …

Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments

2023 · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

Many real-world scenarios in which DNN-based recognition systems are deployed have inherently fine-grained attributes (e.g., bird-species recognition, medical image classification). In addition to achieving reliable accuracy, a critical subtask for these models is to detect …

Understanding magnetoelectric switching in BiFeO$_3$ thin films

2023 · arXiv (Cornell University)

In this work we use a phenomenological theory of ferroelectric switching in BiFeO$_3$ thin films to uncover the mechanism of the two-step process that leads to the reversal of the weak magnetization of these materials. …

Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models

2024 · arXiv (Cornell University)

The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and test data contamination. Despite improved performance, existing methods (including …

A Rapid Risk Assessment Method for Distribution Network Based on K-Nearest Neighbors

2023

High proportion of new energy access makes grid operation uncertainty increase, operation mode adjustment more frequent. In this paper, we developed a rapid risk assessment method for distribution network (DN). First, the collected data from …

Investigating Knowledge Graphs as Structured External Memory to Enhance Large Language Models’ Generation for Mathematical Concept Answering

2024

Interactive question-answering (QA) with a tutor is an effective learning method for middle school math students. The flexibility and emergent capabilities of generative large language models (LLMs) have sparked significant interest in automating this process …

Voice Evaluation of Reasoning Ability: Diagnosing the Modality-Induced Performance Gap

2025 · arXiv (Cornell University)

We present Voice Evaluation of Reasoning Ability (VERA), a benchmark for evaluating reasoning ability in voice-interactive systems under real-time conversational constraints. VERA comprises 2,931 voice-native episodes derived from established text benchmarks and organized into five …