Publications (37)
SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
Keyan Ding, Jing Yu, Junjie Huang +3
Scientific research increasingly relies on specialized computational tools, yet effectively utilizing these tools demands substantial domain expertise. While Large Language Models…
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +46
Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Wi…
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem
Shuofei Qiao, Yunxiang Wei, Xuehai Wang +10
The rapid evolution of Large Language Models has catalyzed a surge in scientific idea production, yet this leap has not been accompanied by a matching advance in idea evaluation. T…
MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules
Tong Xu, Xinzhe Cao, Zhihui Zhu +2
Current molecular generation benchmarks emphasize task complexity, molecule novelty, and property alignment; they largely overlook a critical concern: the potential safety risks of…
KEPLA: A Knowledge-Enhanced Deep Learning Framework for Accurate Protein-Ligand Binding Affinity Prediction
Han Liu, Keyan Ding, Peilin Chen +4
Accurate prediction of protein-ligand binding affinity is critical for drug discovery. While recent deep learning approaches have demonstrated promising results, they often rely so…
Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple LLM Judges
Yuqi Tang, Kehua Feng, Yunfeng Wang +6
Evaluating the conversational abilities of large language models (LLMs) remains a challenging task. Current mainstream approaches primarily rely on the "LLM-as-a-judge" paradigm, w…
A Simple Method to improve Initialization Robustness for Active Contours driven by Local Region Fitting Energy
Keyan Ding, Linfang Xiao
Active contour models based on local region fitting energy can segment images with intensity inhomogeneity effectively, but their segmentation results are easy to error if the init…
Advancing biomolecular understanding and design following human instructions
Xiang Zhuang, Keyan Ding, Tianwen Lyu +9
Understanding and designing biomolecules, such as proteins and small molecules, is central to advancing drug discovery, synthetic biology and enzyme engineering. Recent breakthroug…
SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning
Kehua Feng, Keyan Ding, Yuhao Wang +5
Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical…
SciCUEval: A Comprehensive Dataset for Evaluating Scientific Context Understanding in Large Language Models
Jing Yu, Yuqi Tang, Kehua Feng +8
Large Language Models (LLMs) have shown impressive capabilities in contextual understanding and reasoning. However, evaluating their performance across diverse scientific domains r…
Deep Shape-Texture Statistics for Completely Blind Image Quality Evaluation
Yixuan Li, Peilin Chen, Hanwei Zhu +3
Opinion-Unaware Blind Image Quality Assessment (OU-BIQA) models aim to predict image quality without training on reference images and subjective quality scores. Thereinto, image st…
Intrinsic Image Popularity Assessment
Keyan Ding, Kede Ma, Shiqi Wang
The goal of research in automatic image popularity assessment (IPA) is to develop computational models that can accurately predict the potential of a social image to go viral on th…
Opinion-Unaware Blind Image Quality Assessment using Multi-Scale Deep Feature Statistics
Zhangkai Ni, Yue Liu, Keyan Ding +3
Deep learning-based methods have significantly influenced the blind image quality assessment (BIQA) field, however, these methods often require training using large amounts of huma…
Embodied Science: Closing the Discovery Loop with Agentic Embodied AI
Xiang Zhuang, Chenyi Zhou, Kehua Feng +10
Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit go…
CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning
Kehua Feng, Keyan Ding, Zhihui Zhu +3
While chain-of-thought (CoT) distillation from advanced large language models (LLMs) has proven effective in general reasoning tasks, it struggles in scientific domains where even…
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
Shuofei Qiao, Yunxiang Wei, Jiazheng Fan +8
The exponential growth of global academic output has confronted researchers and AI agents with an unprecedented ``information explosion,'' where fragmented and unstructured knowled…
ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding
Mingyang Rao, Kehua Feng, Zhihui Zhu +4
While Large Language Models (LLMs) have revolutionized scientific text processing, they exhibit a significant capability gap when interpreting chemical reaction diagrams. We identi…
SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
Tianhao Li, Jingyu Lu, Chuangxin Chu +12
Large language models (LLMs) have a transformative impact on a variety of scientific tasks across disciplines including biology, chemistry, medicine, and physics. However, ensuring…
InstructProtein: Aligning Human and Protein Language via Knowledge Instruction
Zeyuan Wang, Qiang Zhang, Keyan Ding +4
Large Language Models (LLMs) have revolutionized the field of natural language processing, but they fall short in comprehending biological sequences such as proteins. To address th…
SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
Kehua Feng, Xinyi Shen, Weijie Wang +4
Large language models (LLMs) are playing an increasingly important role in scientific research, yet there remains a lack of comprehensive benchmarks to evaluate the breadth and dep…
Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition
Kehua Feng, Keyan Ding, Hongzhi Tan +8
Reliable evaluation of large language models (LLMs) is impeded by two key challenges: objective metrics often fail to reflect human perception of natural language, and exhaustive h…
Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra
Yiwen Zhang, Keyan Ding, Yihang Wu +4
Retrieving molecular structures from tandem mass spectra is a crucial step in rapid compound identification. Existing retrieval methods, such as traditional mass spectral library m…
TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval
Yuhang Zhang, Keyan Ding, Peilin Chen +5
Enzyme-reaction retrieval is a fundamental problem in computational biology, underpinning enzyme characterization, reaction mechanism elucidation, and the rational design of metabo…
MolMark: Safeguarding Molecular Structures through Learnable Atom-Level Watermarking
Runwen Hu, Peilin Chen, Keyan Ding +1
AI-driven molecular generation is reshaping drug discovery and materials design, yet the lack of protection mechanisms leaves AI-generated molecules vulnerable to unauthorized reus…
Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization
Yuhao Wang, Keyan Ding, Kehua Feng +5
Protein language models have emerged as powerful tools for sequence generation, offering substantial advantages in functional optimization and denovo design. However, these models…
Comparison of Image Quality Models for Optimization of Image Processing Systems
Keyan Ding, Kede Ma, Shiqi Wang +1
The performance of objective image quality assessment (IQA) models has been evaluated primarily by comparing model predictions to human quality judgments. Perceptual datasets gathe…
Image Quality Assessment: Unifying Structure and Texture Similarity
Keyan Ding, Kede Ma, Shiqi Wang +1
Objective measures of image quality generally operate by comparing pixels of a "degraded" image to those of the original. Relative to human observers, these measures are overly sen…
Graph Sampling-based Meta-Learning for Molecular Property Prediction
Xiang Zhuang, Qiang Zhang, Bin Wu +3
Molecular property is usually observed with a limited number of samples, and researchers have considered property prediction as a few-shot problem. One important fact that has been…
Locally Adaptive Structure and Texture Similarity for Image Quality Assessment
Keyan Ding, Yi Liu, Xueyi Zou +2
The latest advances in full-reference image quality assessment (IQA) involve unifying structure and texture similarity based on deep representations. The resulting Deep Image Struc…
Evaluating Reward Model Generalization via Pairwise Maximum Discrepancy Competitions
Shunyang Luo, Peibei Cao, Zhihui Zhu +3
Reward models (RMs) are central to aligning large language models, yet their practical effectiveness hinges on generalization to unseen prompts and shifting distributions. Most exi…
Learning Invariant Molecular Representation in Latent Discrete Space
Xiang Zhuang, Qiang Zhang, Keyan Ding +5
Molecular representation learning lays the foundation for drug discovery. However, existing methods suffer from poor out-of-distribution (OOD) generalization, particularly when dat…
ClinDEF: A Dynamic Evaluation Framework for Large Language Models in Clinical Reasoning
Yuqi Tang, Jing Yu, Zichang Su +7
Clinical diagnosis begins with doctor-patient interaction, during which physicians iteratively gather information, determine examination and refine differential diagnosis through p…
AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment
Hanwei Zhu, Yu Tian, Keyan Ding +4
Image quality assessment (IQA) is inherently complex, as it reflects both the quantification and interpretation of perceptual quality rooted in the human visual system. Conventiona…
OneEval: Benchmarking LLM Knowledge-intensive Reasoning over Diverse Knowledge Bases
Yongrui Chen, Zhiqiang Liu, Jing Yu +21
Large Language Models (LLMs) have demonstrated substantial progress on reasoning tasks involving unstructured text, yet their capabilities significantly deteriorate when reasoning…
Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning
Xiang Zhuang, Bin Wu, Jiyu Cui +6
Molecular structure elucidation involves deducing a molecule's structure from various types of spectral data, which is crucial in chemical experimental analysis. While large langua…
SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition
Yuqi Tang, Chenyi Zhou, Libin Wang +3
Large language model (LLM) agents have been increasingly adopted in scientific research for organizing and invoking specialized computational tools. However, their reliance on pred…
Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning
Tianwen Lyu, Xiang Zhuang, Keyan Ding +5
Understanding complex biomolecular mechanisms requires multi-step reasoning across molecular interactions, signaling cascades, and metabolic pathways. While large language models(L…