activity
20242026
collaborators

9 papers

q-bio.QM2026

BioHarness: Substrate-Aware Evidence Assembly for Biomedical Question Answering across Literature, Knowledge Bases, and Biological Atlases

Meng Xiao, Chuan Qin, Jinmiao Chen +3

Motivation: Biomedical question answering often requires evidence beyond topically retrieved literature, including gene alias resolution, database identifier normalization, and atl…

q-bio.GN2026

SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding

Xiaohan Huang, Meng Xiao, Chuan Qin +4

Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks. However, their ability to reliably reason fr…

cs.LG2026

From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow Matching

Siyu Pu, Qingqing Long, Xiaohan Huang +7

Single-cell RNA sequencing (scRNA-seq) provides high-dimensional profiles of cellular states, enabling data-driven modeling of cellular dynamics over time. In practice, time-resolv…

cs.CL2026

DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering

Haotian Chen, Qingqing Long, Siyu Pu +6

With the rapid growth of scientific literature, scientific question answering (SciQA) has become increasingly critical for exploring and utilizing scientific knowledge. Retrieval-A…

cs.CL2025

Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training

Meng Xiao, Xunxin Cai, Qingqing Long +3

Corpus distillation for biomedical large language models (LLMs) seeks to address the pressing challenge of insufficient quantity and quality in open-source annotated scientific cor…

cs.CL2025

Knowledge Hierarchy Guided Biological-Medical Dataset Distillation for Domain LLM Training

Xunxin Cai, Chengrui Wang, Qingqing Long +2

The rapid advancement of large language models (LLMs) in biological-medical applications has highlighted a gap between their potential and the limited scale and often low quality o…