Jian Tang

Biographie

Jian Tang est professeur agrégé au département de sciences de la décision de HEC. Il est aussi professeur associé au département informatique et recherche opérationnelle (DIRO) de l'Université de Montréal et un membre académique principal à Mila – Institut québécois d’intelligence artificielle. Il est titulaire d'une chaire de recherche en IA Canada-CIFAR et le fondateur de BioGeometry, une entreprise en démarrage spécialisée dans l'IA générative pour la découverte d'anticorps. Ses principaux domaines de recherche sont les modèles génératifs profonds, l'apprentissage automatique des graphes et leurs applications à la découverte de médicaments. Il est un leader international dans le domaine de l'apprentissage automatique des graphes, et son travail représentatif sur l'apprentissage de la représentation des nœuds, LINE, a été largement reconnu et cité plus de 5 000 fois. Il a également réalisé de nombreux travaux pionniers sur l'IA pour la découverte de médicaments, notamment le premier cadre d'apprentissage automatique à source ouverte pour la découverte de médicaments, TorchDrug et TorchProtein.

Étudiants actuels

Huiyu Cai

Doctorat - UdeM

huiyu.cai@mila.quebec

Collaborateur·rice de recherche

Farzana Heidari

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Doctorat - UdeM

Github

Shentong Mo

Collaborateur·rice de recherche - Carnegie Mellon University

Chence Shi

Doctorat - UdeM

Yu Tianshu

Visiteur de recherche indépendant - Chinese University of Hong Kong

Sophie Xhonneux

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Gauthier Gidel

lpxhonneux@gmail.com

Xinyu Yuan

Doctorat - UdeM

xinyu.yuan@mila.quebec

Github

zhaocheng.zhu@umontreal.ca

Zhihao Zhan

Doctorat - UdeM

Doctorat - UdeM

Doctorat - HEC

Jianan Zhao

Doctorat - UdeM

Doctorat - UdeM

Github

Publications

Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models

Zhanke Zhou

Zhaocheng Zhu

Xuan Li

Mikhail Galkin

Xiao Feng

Sanmi Koyejo

Bo Han

Numerous applications of large language models (LLMs) rely on their ability to perform step-by-step reasoning. However, the reasoning behavi… (voir plus)or of LLMs remains poorly understood, posing challenges to research, development, and safety. To address this gap, we introduce landscape of thoughts-the first visualization tool for users to inspect the reasoning paths of chain-of-thought and its derivatives on any multi-choice dataset. Specifically, we represent the states in a reasoning path as feature vectors that quantify their distances to all answer choices. These features are then visualized in two-dimensional plots using t-SNE. Qualitative analysis shows that the landscape of thoughts effectively distinguishes between strong and weak models, correct and incorrect answers, as well as different reasoning tasks. It also uncovers undesirable reasoning patterns, such as low consistency and high uncertainty. Additionally, users can adapt our tool to a model that predicts any property they observe. We showcase this advantage by adapting our tool to a lightweight verifier, which significantly improves reasoning by evaluating the correctness of reasoning paths. The code is publicly available at https://github.com/tmlr-group/landscape-of-thoughts.

2025-07-09

ICML.cc/2025/Workshop/AI4MATH (poster)

DOLPHIN advances single-cell transcriptomics beyond gene level by leveraging exon and junction reads

Kailu Song

Yumin Zheng

Bowen Zhao

David H. Eidelman

Jun Ding

2025-07-04

Nature Communications (publié)

Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models

Zhanke Zhou

Zhaocheng Zhu

Xuan Li

Mikhail Galkin

Xiao Feng

Sanmi Koyejo

Bo Han

2025-06-30

ICML.cc/2025/Workshop/R2-FM (poster)

FORT: Forward-Only Regression Training of Normalizing Flows

Oscar Davis

Michael M. Bronstein

Alexander Tong

Simulation-free training frameworks have been at the forefront of the generative modelling revolution in continuous spaces, leading to neura… (voir plus)l dynamical systems that encompass modern large-scale diffusion and flow matching models. Despite the scalability of training, the generation of high-quality samples and their corresponding likelihood under the model requires expensive numerical simulation -- inhibiting adoption in numerous scientific applications such as equilibrium sampling of molecular systems. In this paper, we revisit classical normalizing flows as one-step generative models with exact likelihoods and propose a novel, scalable training objective that does not require computing the expensive change of variable formula used in conventional maximum likelihood training. We propose Forward-Only Regression Training (FORT), a simple

2025-06-11

ICML.cc/2025/Workshop/GenBio (spotlight)

Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention

Efficient long-context modeling remains a critical challenge for natural language processing (NLP), as the time complexity of the predominan… (voir plus)t Transformer architecture scales quadratically with the sequence length. While state-space models (SSMs) offer alternative sub-quadratic solutions, they struggle to capture long-range dependencies effectively. In this work, we focus on analyzing and improving the long-context modeling capabilities of SSMs. We show that the widely used synthetic task, associative recall, which requires a model to recall a value associated with a single key without context, insufficiently represents the complexities of real-world long-context modeling. To address this limitation, we extend the associative recall to a novel synthetic task, \emph{joint recall}, which requires a model to recall the value associated with a key given in a specified context. Theoretically, we prove that SSMs do not have the expressiveness to solve multi-query joint recall in sub-quadratic time complexity. To resolve this issue, we propose a solution based on integrating SSMs with Context-Dependent Sparse Attention (CDSA), which has the expressiveness to solve multi-query joint recall with sub-quadratic computation. To bridge the gap between theoretical analysis and real-world applications, we propose locality-sensitive Hashing Attention with sparse Key Selection (HAX), which instantiates the theoretical solution and is further tailored to natural language domains. Extensive experiments on both synthetic and real-world long-context benchmarks show that HAX consistently outperforms SSM baselines and SSMs integrated with context-independent sparse attention (CISA).

2025-06-11

ICML.cc/2025/Workshop/ES-FoMo-III (publié)

Self-Evolving Curriculum for LLM Reasoning

Minsu Kim

Alex Pich'e

Nicolas Gontier

Yoshua Bengio

Ehsan Kamalloo

2025-05-20

ArXiv (prépublication)

arxiv.org

Aligning Protein Conformation Ensemble Generation with Physical Feedback

Xiaoyin Chen

Stephen Zhewen Lu

Aurelie Lozano

Vijil Chenthamarakshan

Payel Das

Protein dynamics play a crucial role in protein biological functions and properties, and their traditional study typically relies on time-co… (voir plus)nsuming molecular dynamics (MD) simulations conducted in silico. Recent advances in generative modeling, particularly denoising diffusion models, have enabled efficient accurate protein structure prediction and conformation sampling by learning distributions over crystallographic structures. However, effectively integrating physical supervision into these data-driven approaches remains challenging, as standard energy-based objectives often lead to intractable optimization. In this paper, we introduce Energy-based Alignment (EBA), a method that aligns generative models with feedback from physical models, efficiently calibrating them to appropriately balance conformational states based on their energy differences. Experimental results on the MD ensemble benchmark demonstrate that EBA achieves state-of-the-art performance in generating high-quality protein ensembles. By improving the physical plausibility of generated structures, our approach enhances model predictions and holds promise for applications in structural biology and drug discovery.

2025-05-01

ICML.cc/2025/Conference (poster)

Self-Evolving Curriculum for LLM Reasoning

Minsu Kim

Alexandre Piché

Nicolas Gontier

Yoshua Bengio

Ehsan Kamalloo

2025-05-01

arXiv (publié)

arxiv.org

A Text-guided Protein Design Framework

Shengchao Liu

Yanjing Li

Zhuoxinran Li

Anthony Gitter

Yutao Zhu

Zhao Xu

Weili Nie

Arvind Ramanathan

Chaowei Xiao

Hongyu Guo

Animashree Anandkumar

2025-03-27

Nature Machine Intelligence (publié)

arxiv.org

Towards Protein Sequence & Structure Co-Design with Multi-Modal Language Models

Stephen Zhewen Lu

Hongyu Guo

Proteins perform diverse biological functions, governed by the intricate relationship between their sequence and three-dimensional structure… (voir plus). While protein language models (PLMs) have demonstrated remarkable success in functional annotation and structure prediction, their potential for sequence-structure co-design remains underexplored. This limitation arises from pre-training objectives that favor masked token prediction over generative modeling. In this work, we systematically explore sampling strategies to enhance the generative capabilities of PLMs for co-design. Notably, we introduce a ranked iterative decoding with re-masking scheme, enabling PLMs to generate sequences and structures more effectively. Benchmarking ESM3 across multiple scales, we demonstrate that using PLMs effectively at sampling time for co-design tasks can outperform specialized architectures that lack comparable scaling properties. Our work advances the field of computational protein design by equipping PLMs with robust generative capabilities tailored to sequence-structure interdependence.

2025-03-06

ICLR.cc/2025/Workshop/LMRL (publié)

Towards Protein Sequence & Structure Co-Design with Multi-Modal Language Models

Stephen Zhewen Lu

Hongyu Guo

2025-03-06

ICLR.cc/2025/Workshop/LMRL (publié)

Design of Ligand-Binding Proteins with Atomic Flow Matching

Junqi Liu

Shaoning Li

Chence Shi

Zhi Yang

2025-03-05

ICLR.cc/2025/Workshop/GEM (publié)