Government
Jinyang Li
Text-to-SQL parsing, which aims at converting natural language questions into executable SQLs, has gained increasing attention in recent years.
Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
We study the task of learning SIMs in the agnostic (a.k.a.
To Believe or Not to Believe Y our LLM: Iterative Prompting for Estimating Epistemic Uncertainty
We explore uncertainty quantification in large language models (LLMs), with the goal to identify when uncertainty in responses given a query is large. We simultaneously consider both epistemic and aleatoric uncertainties, where the former comes from the lack of knowledge about the ground truth (such as about facts or the language), and the latter comes from irreducible randomness (such as multiple possible answers).
A Probability Contrastive Learning Framework for 3D Molecular Representation Learning
It has inspired various applications in molecular property prediction and drug design.
As Sudanese city returns to life after two-year siege, drone threat lingers
Life is cautiously returning to the streets of Dilling, the second largest city in South Kordofan state, after the Sudanese army broke a suffocating siege that had isolated the area for more than two years. For months, the city had been encircled by the paramilitary Rapid Support Forces (RSF) and the Sudan People's Liberation Movement-North (SPLM-N), cutting off vital supply lines and trapping civilians in a severe humanitarian crisis. Al Jazeera Arabic's Hisham Uweit, reporting from Dilling, described a city "recovering slowly" from the economic strangulation. "For over two years, heavy siege conditions were imposed on the city. Movement disappeared, goods vanished and livelihoods narrowed," Uweit said.
