MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark
1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs
One Language, Many Gaps: Evaluating Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks
Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
CERD: A Comprehensive Chinese Rhetoric Dataset for Rhetorical Understanding and Generation in Essays
Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method
Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning
Meta Reasoning for Large Language Models
Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction
LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models
Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
Low-code LLM: Graphical User Interface over Large Language Models
Research Experience
Senior Research Software Engineer at Microsoft Research Asia's General AI Group; volunteer reviewer for top-tier conferences and journals including NeurIPS, ICLR, ICML, ACL ARR, etc.
Education
Master's degree in Computer Science from Tsinghua University (2019), Bachelor's degree in Computer Science from Beijing Normal University (2016)
Background
Senior Research Software Engineer, specializing in artificial intelligence, large language models, natural language processing, and agent systems. Main focus is on developing next-generation LLM-powered agent systems to enhance reasoning, planning, and task-solving capabilities.
Miscellany
Widely interested in various topics, more can be found in the 'gallery' tab of the personal website.