Longxiang Liu

3 papers · 2021–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird

Venues

AAAI (2) EMNLP (1)

Top co-authors

Chenghao Yang (1) Yang Feng (1) Ge Zhang (1) Jianpeng Jiao (1) Qi Chu (1) Tao Gong (1) Kaiyuan Zhang (1) Hai Zhao (1) Nenghai Yu (1) Yinbo Luo (1)

Research topics

Machine Learning (3) Natural Language Processing (3) Generation (3) Deep Learning (2) Core Methods (2) Learning Types · Deep Learning (2) Artificial Intelligence (1) Reinforcement Learning (1) Core AI (1) Learning Types · Machine Learning (1) Methods (1) Optimization & Theory (1)

Keywords

multi-turn dialogue (2) policy learning (1) dialogue history (1) dialogue evaluation (1) dialogue system (1) scheduled sampling (1) dialog generation (1) task-oriented dialog (1) utterance representation (1) speaker representation (1) attention visualization (1) large language model (1) policy generation (1) dialog policy (1) multi-task objective (1) action tree (1) state label (1) utterance-aware representation (1) multi-task learning (1) speaker-aware representation (1)

Papers

MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation EMNLP 2025 TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling AAAI 2024 Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue AAAI 2021