Le Song

Le Song

Auto-generated profile, based on publicly available information

Le Song

Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 November 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
DZDuzhen Zhang
Duzhen Zhang
ZLZhong-Zhi Li
Zhong-Zhi Li
MZMing-Liang Zhang
Ming-Liang Zhang
JZJiaxin Zhang
Jiaxin Zhang
ZLZengyan Liu
Zengyan Liu
CLCheng-Lin Liu
Cheng-Lin Liu
Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in quick, heuristic decisions, System 2 relies on logical reasoning for more accurate judgments and reduced biases. Foundational Large Language Models (LLMs) excel at fast decision-making but lack the depth for complex reasoning, as they have not yet fully embraced the step-by-step analysis characteristic of true System 2 thinking. Recently, reasoning LLMs like OpenAI’s o1/o3 and DeepSeek’s R1 have demonstrated expert-level performance in fields such as mathematics and coding, closely mimicking the deliberate reasoning of System 2 and showcasing human-like cognitive abilities. This survey begins with a brief overview of the progress in foundational LLMs and the early development of System 2 technologies, exploring how their combination has paved the way for reasoning LLMs. Next, we discuss how to construct reasoning LLMs, trace the evolution of various reasoning models, and examine the core methods that enable advanced reasoning behind them. Additionally, we provide an overview of reasoning benchmarks, offering an in-depth comparison of the performance of representative reasoning LLMs. Finally, we explore promising directions for advancing reasoning LLMs and maintain a real-time GitHub Repository to track the latest developments. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this rapidly evolving field.

19 February 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
ECElijah Cole
Elijah Cole
GHGeert-Jan Huizing
Geert-Jan Huizing
SASohan Addagudi
Sohan Addagudi
NHNicholas Ho
Nicholas Ho
EHEuxhen Hasanaj
Euxhen Hasanaj
EXEric P. Xing
Eric P. Xing
Predicting cellular responses to genetic or chemical perturbations is a long-standing goal in biology. Recent applications of foundation models to this task have yielded contradictory results regarding their superiority over simple baselines. We conducted an extensive analysis of the utility of pretrained embeddings (including but not limited to biological foundation models) for perturbation response prediction, covering over 600 embedding-task pairs. While some foundation models fail to outperform simple baselines, others yield consistent improvements. However, the strongest pretrained embeddings are those derived from prior knowledge. We also developed methods for integrating multiple pretrained embeddings to make better predictions. Our results confirm that pretrained embeddings can enable more accurate simulations of cellular behavior. Code and Data: https://github.com/genbio-ai/foundation-models-perturbation

1 February 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HXHuan Xiong
Huan Xiong
LHLei Huang
Lei Huang
WZWenston J.T. Zang
Wenston J.T. Zang
XZXiantong Zhen
Xiantong Zhen
Guosen XieGuosen Xie
Guosen Xie
LSLe Song
Le Song
One fundamental problem in deep learning is understanding the excellent performance of deep Neural Networks (NNs) in practice. An explanation for the superiority of NNs is that they can realize a large family of complicated functions, i.e., they have powerful expressivity. The expressivity of a Neural Network with Piecewise Linear activations (PLNN) can be quantified by the maximal number of linear regions it can separate its input space into. In this paper, we provide several mathematical results needed for studying the linear regions of Convolutional Neural Networks with Piecewise Linear activations (PLCNNs), and use them to derive the maximal and average numbers of linear regions for one-layer PLCNNs. Furthermore, we obtain upper and lower bounds for the number of linear regions of multi-layer PLCNNs. Our results suggest that deeper PLCNNs have more powerful expressivity than shallow PLCNNs, while PLCNNs have more expressivity than fully-connected PLNNs per parameter, in terms of the number of linear regions.

14 April 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
XCXingyi Cheng
Xingyi Cheng
PLPan Li
Pan Li
HGHan Guo
Han Guo
YLYouwei Liang
Youwei Liang
JGJing Gong
Jing Gong
EXEric Xing
Eric Xing
A virtual cell is a world model of a cell: a computational system that predicts, simulates and programs cellular processes across modalities and scales. An important path toward this goal is to model how genetic and chemical perturbations give rise to transcriptional responses, a core capability for disease understanding and drug discovery. However, current approaches remain expert-intensive, relying on iterative manual model design, training and debugging over months. Here we present VCHarness, an autonomous AI system that constructs perturbation-response models by combining an AI coding agent with multimodal biological foundation models. The system explores large spaces of architectures and training pipelines with minimal human intervention, iteratively generating, evaluating and refining candidate models. Across multiple perturbation-response benchmarks, VCHarness identifies architectures that outperform expert-designed approaches while reducing development time from months to days. It further uncovers non-obvious architectural patterns associated with improved performance, indicating that automated search can extend beyond conventional design strategies. These results suggest a shift from manually engineered models toward autonomous systems for constructing components of virtual cell world models, enabling scalable and data-driven exploration of cellular systems.

20 March 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
SKSaarthak Kapse
Saarthak Kapse
MAMehmet Aygün
Mehmet Aygün
ECElijah Cole
Elijah Cole
ELEmma Lundberg
Emma Lundberg
LSLe Song
Le Song
EXEric P. Xing
Eric P. Xing
Recent advancements in histopathology foundation models (FMs) have largely been driven by scaling the training data, often utilizing massive proprietary datasets. However, the long-tailed distribution of morphological features in whole-slide images (WSIs) makes simple scaling inefficient, as common morphologies dominate the learning signal. We introduce GenBio-PathFM, a 1.1B-parameter FM that achieves state-of-the-art performance on public benchmarks while using a fraction of the training data required by current leading models. The efficiency of GenBio-PathFM is underpinned by two primary innovations: an automated data curation pipeline that prioritizes morphological diversity and a novel dual-stage learning strategy which we term JEDI ( JE PA + DI NO). Across the THUNDER, HEST, and PathoROB benchmarks, GenBio-PathFM demonstrates state-of-the-art accuracy and robustness. GenBio-PathFM is the strongest open-weight model to date and the only state-of-the-art model trained exclusively on public data.