Qiang Liu

AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration

PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization

Disentangling Knowledge Representations for Large Language Model Editing

ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models

SpectraLLM: Uncovering the Ability of LLMs for Molecule Structure Elucidation from Multi-Spectra

Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention

VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks

C$^3$-Bench: Evaluating and Achieving Controllable Code Completion in Code LLM

Binding Mode Matters: Residue-Guided Drug Discovery via Explorative Preferences

From Genomic Whispers to Therapeutics: Multi-Resolution Transcriptome-Guided Diffusion Models for Drug Design and Screening

Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

Uncovering Overfitting in Large Language Model Editing

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing

MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra

Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows

Graffe: Graph Representation Learning Enabled via Diffusion Probabilistic Models

Dual Flows with Contrastive Guidance for Generating Highly Designable Proteins

Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining