Cao Ruisheng

icon indicating a website link https://rhythmcao.github.io/ icon indicating an email [email protected]

icon company Shanghai Jiao Tong University icon location No.800 Dongchuan Road, Minhang District, Shanghai, China icon location Currently a PhD candidate student in Shanghai Jiao Tong University (SJTU). Research interests include structured NLP/NLG and LLM/VLM-based multimodal agents.

Results 14 comments of Cao Ruisheng

Question about the edge features

They are both initialized from an embedding matrix, similar to that in RATSQL.

支持cspider数据集训练

Two schemes： 1. Use an off-the-shelf translator to translate Chinese question into English, and directly apply the model. 2. Use a multi-lingual PLM to replace BERT. Notice that the schema...

How to add values generation ?

For value generation in a grammar-based parser, you can see my repository [ASTormer](https://github.com/rhythmcao/text-to-sql-astormer) for details, which adopts a pointer-generator network for value generation.

OpenAI API Streaming Error: 500 Unknown method llama.cpp with unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF

Maybe the error is raised by the old jinja version which does not support the `reject` filter (required jinja version >=2.7, see [doc](https://docs.jinkan.org/docs/jinja2/templates.html#reject)). Try replacing the following statement in the...