Qi Liu

30

Papers

358

Total Citations

Papers (30)

OctoPack: Instruction Tuning Code Large Language Models

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Zero-1-to-3: Domain-Level Zero-Shot Cognitive Diagnosis via One Batch of Early-Bird Students towards Three Diagnostic Objectives

Agent4Edu: Generating Learner Response Data by Generative Agents for Intelligent Education Systems

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation

AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction

Precision-Enhanced Human-Object Contact Detection via Depth-Aware Perspective Interaction and Object Texture Restoration

Semi-IIN: Semi-Supervised Intra-Inter Modal Interaction Learning Network for Multimodal Sentiment Analysis

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

LLM Agents Can Be Choice-Supportive Biased Evaluators: An Empirical Study

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

CursorCore: Assist Programming through Aligning Anything

Toy-GS: Assembling Local Gaussians for Precisely Rendering Large-Scale Free Camera Trajectories

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

A Unified Adaptive Testing System Enabled by Hierarchical Structure Search

Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss

MSA2: Multi-task Framework with Structure-aware and Style-adaptive Character Representation for Open-set Chinese Text Recognition

GenAL: Generative Agent for Adaptive Learning

Geometry-Aware 3D Salient Object Detection Network

Distribution-Driven Dense Retrieval: Modeling Many-to-One Query-Document Relationship

SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning

VERSE: Verification-based Self-Play for Code Instructions

ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization

Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision

R3CD: Scene Graph to Image Generation with Relation-Aware Compositional Control Diffusion

CONSIDER: Commonalities and Specialties Driven Multilingual Code Retrieval Framework

Improving Depth Completion via Depth Feature Upsampling

Federated Self-Explaining GNNs with Anti-shortcut Augmentations

VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models