Qi Liu

Full Professor@University of Science and Technology of China·中国·OpenReview

研究方向

intelligent education · cognitive diagnosis · knowledge tracing · educational big data · recommender systems · social network analysis · machine learning · data mining

Qi Liu

Fewer Battles, More Gain: An Information-Efficient Framework for Arena-based LLM Evaluation

Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward

ChemEval: A Multi-level and Fine-grained Chemical Capability Evaluation for Large Language Models

Not All Code Helps: Disentangling the Impact of Code Data on Mathematical Reasoning in Large Language Models

Visual Autoregressive Modeling for Instruction-Guided Image Editing

EffSelect: Efficient Feature Value Selection for Deep Recommender Systems with Mini-Batch Training

Beneath the Surface: Exposing and Mitigating Surface Learning in Large Language Models

Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables

Conditional Guided Flow Matching: Modeling Prediction Residuals for Enhanced Time Series Forecasting

Find tailored step example for next step: A Targeted Step-wise Retrieval Framework for Guiding LLM Reasoning

From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization

Multimodal Forecasting of Sparse Intraoperative Hypotension Events Powered by Language Model

Auditing Test Data Contamination with Error Rate Control for Reliable LLM Evaluation

BioDataLab: Towards Generalist Agents for Real-world Biological Data Engineering

ScholarSum: Student-Teacher Abstractive Summarization via Knowledge Graph Reasoning and Reflective Refinement

Improving Time Series Forecasting via Instance-aware Post-hoc Revision

TimeDART: A Diffusion Autoregressive Transformer for Self-Supervised Time Series Representation

am-ELO: A Stable Framework for Arena-based LLM Evaluation

Personalized Visual Content Generation in Conversational Systems

CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective

A Closed-Form Solution for Fast and Reliable Adaptive Testing

CursorCore: Assist Programming through Aligning Anything

CursorCore: Assist Programming through Aligning Anything

Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study

Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment

CAD-Editor: Text-based CAD Editing through Adapting Large Language Models with Synthetic Data

Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting

CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing

TestAgent: An Adaptive and Intelligent Expert for Human Assessment

Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models

CogMath: Evaluating LLMs' Authentic Mathematical Ability from a Cognitive Perspective

PoTable: Programming Standardly on Table-based Reasoning Like a Human Analyst

LINA: An LLM-driven Neuro-Symbolic Approach for Faithful Logical Reasoning

Beyond Layers: A Global Message-Passing Mechanism for Heterophilic Graphs