17 citations · 21 across the 8 of their papers we have counts for
10 papers
SWEPatchTest: Evaluating Software Tests Beyond Reproduction
Hua Lu, Pengcheng Wang, Han Li +4
Coding agents use generated tests to decide whether a proposed patch satisfies an issue's requirements. A suite that fails on the buggy program and passes after applying the refere…
Practice on Long Behavior Sequence Modeling in Tencent Advertising
Xian Hu, Ming Yue, Zhixiang Feng +24
Long-sequence modeling has become an indispensable frontier in recommendation systems for capturing users' long-term preferences. However, user behaviors within advertising domains…
A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future
Jialun Zhong, Wei Shen, Yanzeng Li +7
Reward Model (RM) has demonstrated impressive potential for enhancing Large Language Models (LLM), as RM can serve as a proxy for human preferences, providing signals to guide LLMs…
DILI: A Distribution-Driven Learned Index (Extended version)
Pengfei Li, Hua Lu, Rong Zhu +3
Targeting in-memory one-dimensional search keys, we propose a novel DIstribution-driven Learned Index tree (DILI), where a concise and computation-efficient linear regression model…
PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation
Siqi Bao, Huang He, Jun Xu +7
Recently, the practical deployment of open-domain dialogue systems has been plagued by the knowledge issue of information deficiency and factual inaccuracy. To this end, we introdu…
Towards Boosting the Open-Domain Chatbot with Human Feedback
Hua Lu, Siqi Bao, Huang He +3
Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses when interacting with real…
Towards Building an Open-Domain Dialogue System Incorporated with Internet Memes
Hua Lu, Zhen Guo, Chanjuan Li +3
In recent years, Internet memes have been widely used in online chatting. Compared with text-based communication, conversations become more expressive and attractive when Internet…
Relational Surrogate Loss Learning
Tao Huang, Zekang Li, Hua Lu +6
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. Thi…
PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation
Siqi Bao, Huang He, Fan Wang +11
To explore the limit of dialogue generation pre-training, we present the models of PLATO-XL with up to 11 billion parameters, trained on both Chinese and English social media conve…
Learning to Select External Knowledge with Multi-Scale Negative Sampling
Huang He, Hua Lu, Siqi Bao +4
The Track-1 of DSTC9 aims to effectively answer user requests or questions during task-oriented dialogues, which are out of the scope of APIs/DB. By leveraging external knowledge r…