activity
20162025
most citedRethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models

22 citations · 70 across the 10 of their papers we have counts for

collaborators

21 papers

cs.CL2025

The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?

Yutao Sun, Mingshuai Chen, Tiancheng Zhao +3

Self-improving large language models (LLMs) -- i.e., to improve the performance of an LLM by fine-tuning it with synthetic data generated by itself -- is a promising way to advance…

cs.CL2021

SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering

Xiaopeng Lu, Kyusong Lee, Tiancheng Zhao

Although open-domain question answering (QA) draws great attention in recent years, it requires large amounts of resources for building the full system and is often difficult to re…

cs.CV2021

VisualSparta: An Embarrassingly Simple Approach to Large-scale Text-to-Image Search with Weighted Bag-of-words

Xiaopeng Lu, Tiancheng Zhao, Kyusong Lee

Text-to-image retrieval is an essential task in cross-modal information retrieval, i.e., retrieving relevant images from a large and unlabelled dataset given textual queries. In th…

cs.CL20204 cited

SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval

Tiancheng Zhao, Xiaopeng Lu, Kyusong Lee

We introduce SPARTA, a novel neural retrieval method that shows great promise in performance, generalization, and interpretability for open-domain question answering. Unlike many n…

cs.CL20206 cited

Report from the NSF Future Directions Workshop, Toward User-Oriented Agents: Research Directions and Challenges

Maxine Eskenazi, Tiancheng Zhao

This USER Workshop was convened with the goal of defining future research directions for the burgeoning intelligent agent research community and to communicate them to the National…

cs.CL20203 cited

Talk to Papers: Bringing Neural Question Answering to Academic Search

Tianchang Zhao, Kyusong Lee

We introduce Talk to Papers, which exploits the recent open-domain question answering (QA) techniques to improve the current experience of academic search. It's designed to enable…