Junwei (Jaden) Liao
jwliao dot ai at gmail dot com
I am a senior undergrad majoring in Artificial Intelligence at
Xi'an Jiaotong University
and was once a visiting student at
University of California, Berkeley
2023 Fall. I am now doing RA at Shanghai Jiao Tong University and will start my PhD in Fall 2025, under the supervision of Weinan Zhang.
I am interested in Reinforcement Learning, Large Decision Models,
specifically LLM-based Agents and unleashing the full potential of Agents
through RL and other advanced techniques.
Email /
GitHub /
LinkedIn
|
|
Education
|
Research Experience
|
Publications
Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
Qiqiang Lin*,
Muning Wen*,
Qiuying Peng*,
Guanyu Nie,
Junwei Liao,
Jun Wang,
Xiaoyun Mo,
Jiamu Zhou,
Cheng Cheng,
Yin Zhao,
Jun Wang,
Weinan Zhang
The Thirteenth International Conference on Learning Representations (ICLR), 2025
arXiv / code / html / dataset and
models
In this paper, we introduce Hammer, a novel family of foundation
models specifically engineered for on-device function calling. Hammer employs
an augmented dataset that enhances models' sensitivity to irrelevant functions and
incorporates function masking techniques to minimize misleading.
|
Preprints
|
|