Spreadsheet-RL: Training Spreadsheet Agents with Real Excel and Reinforcement Learning

Paper / Project page / Code / Dataset / Model Spreadsheet software is one of the most ordinary, durable, and quietly difficult interfaces in computing. A spreadsheet can be a small personal budget, a messy monthly close workbook, an investment-banking model, a sales report, a supply-chain planning sheet, or a hand-built database that has survived for years because it works just well enough. That makes spreadsheets a natural target for AI agents: many people would like to say what they want, let the system edit the workbook, and receive a correct final file....

June 6, 2026 · 16 min · Banghao Chi

LLMarking: Adaptive Automatic Short-Answer Grading Using Large Language Models

This is the official repo for Automatic Short Answer Grading (ASAG) project, named LLMarking, from Xi’an Jiaotong Liverpool University (XJTLU). Using vLLM as the Large Language Model (LLM) inference framework and FastAPI as the HTTP service framework, this project can achieve high throughput of both LLM tokens delivered and request handling. Feature This project aims to achieve high concurrency automatic short answer grading (ASAG) system and implement the construction of service....

June 12, 2024 · 3 min · Banghao Chi

Quantization on CenterPoint

Take mmdetection as an example First find the Runner class: This is the place where the build of the model is completed: class Runner: def __init__(...): ... ... self.model = self.build_model(model) # wrap model self.model = self.wrap_model( self.cfg.get('model_wrapper_cfg'), self.model) # get model name from the model class if hasattr(self.model, 'module'): self._model_name = self.model.module.__class__.__name__ else: self._model_name = self.model.__class__.__name__ ... ... Learn about how pytorch-quantization works by diving into its source code: Code about the quantization function respect to a specific Pytorch model as input: quant_utils....

April 1, 2024 · 7 min · Banghao Chi