Qiang Zhang

Principal Researcher@Zhejiang University·中国·OpenReview

研究方向

molecular and protein representation learning · machine learning · meta-learning · natural language processing · fact checking · temporal point processes

Qiang Zhang

CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning

Adaptive Curriculum Learning for RLHF with Influence-Based Cluster Bandits

FaithThinker: Dialectical Reasoning for Noise-Robust LLMs

Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning

Beyond Geometry: Functionally Grounded Molecule Generation for Structure-Based Drug Design

Knowledge-enhanced MCTS for LLM-based Medical Diagnosis Reasoning

Can Large Language Models Think Like Doctors? An Interactive Approach to Evaluating Clinical Reasoning

Trajectory-Aware Verbalized Optimization for Multi-Agent Systems

UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery

HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts

SaMer: A Scenario-aware Multi-dimensional Evaluator for Large Language Models

Direct Preference Optimization Using Sparse Feature-level Constraints

Constrain Alignment with Sparse Autoencoders

SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models

SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks

scKGOT: Intercellular Signaling Inference with Knowledge Graph Optimal Transport for Single-cell Transcriptomics