Yang Liu

Yang Liu

The advent of large language models (LLMs) has brought about a revolution in the development of tailored machine learning models and sparked debates on redefining data requirements. The automation facilitated by the training and implementation of LLMs has led to discussions and aspirations that human-level labeling interventions may no longer hold the same level of importance as in the era of supervised learning. This paper presents compelling arguments supporting the ongoing relevance of human-labeled data in the era of LLMs.

Peng Wu, Haoxuan Li, Chunyuan Zheng et al. · pku

Counterfactual inference aims to estimate the counterfactual outcome at the individual level given knowledge of an observed treatment and the factual outcome, with broad applications in fields such as epidemiology, econometrics, and management science. Previous methods rely on a known structural causal model (SCM) or assume the homogeneity of the exogenous variable and strict monotonicity between the outcome and exogenous variable. In this paper, we propose a principled approach for identifying and estimating the counterfactual outcome. We first introduce a simple and intuitive rank preservation assumption to identify the counterfactual outcome without relying on a known structural causal model. Building on this, we propose a novel ideal loss for theoretically unbiased learning of the counterfactual outcome and further develop a kernel-based estimator for its empirical estimation. Our theoretical analysis shows that the rank preservation assumption is not stronger than the homogeneity and strict monotonicity assumptions, and shows that the proposed ideal loss is convex, and the proposed estimator is unbiased. Extensive semi-synthetic and real-world experiments are conducted to demonstrate the effectiveness of the proposed method.

Samuel Albanie, Yang Liu, Arsha Nagrani et al.

We present a new video understanding pentathlon challenge, an open competition held in conjunction with the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020. The objective of the challenge was to explore and evaluate new methods for text-to-video retrieval-the task of searching for content within a corpus of videos using natural language queries. This report summarizes the results of the first edition of the challenge together with the findings of the participants.

Jun Pang, Yang Liu, Sjouke Mauw

The present volume contains the proceedings of the Fourth International Workshop on Engineering Safety and Security Systems (ESSS'15). The workshop was held in Oslo, Norway, on June 22nd, 2015, as a satellite event of the 20th International Symposium on Formal Methods (FM'15).

Jun Pang, Yang Liu

The International Workshop on Engineering Safety and Security Systems (ESSS) aims at contributing to the challenge of constructing reliable and secure systems. The workshop covers areas such as formal specification, type checking, model checking, program analysis/transformation, model-based testing and model-driven software construction. The workshop will bring together researchers and industry R&D expertise together to exchange their knowledge, discuss their research findings, and explore potential collaborations. The main theme of the workshop is methods and techniques for constructing large reliable and secure systems. The goal of the workshop is to establish a platform for the exchange of ideas, discussion, cross-fertilization, inspiration, co-operation, and dissemination.