Portrait de Bang Liu

Bang Liu

Membre académique associé
bang.liu@mila.quebec
Chaire en IA Canada-CIFAR
Professeur agrégé, Université de Montréal, Département d'informatique et de recherche opérationnelle
Sujets de recherche
Apprentissage profond
Apprentissage sur graphes
Exploration des données
Modèles génératifs
Traitement du langage naturel
Site web
Google Scholar

Biographie

Bang Liu est professeur adjoint au Département d'informatique et de recherche opérationnelle (DIRO) de l'Université de Montréal. Il est membre du Laboratoire de recherche appliquée en linguistique informatique (RALI) du DIRO, membre associé de Mila – Institut québécois d'intelligence artificielle, et titulaire d'une chaire en IA Canada-CIFAR.

Il a obtenu un baccalauréat en ingénierie de l'Université des sciences et technologies de Chine (USTC) en 2013, ainsi qu’une maîtrise ès sciences et un doctorat de l'Université de l'Alberta en 2015 et en 2020, respectivement. Ses recherches portent principalement sur le traitement du langage naturel, l'apprentissage multimodal et incarné, la théorie et les techniques de l'intelligence artificielle (par exemple, la compréhension et l'amélioration de grands modèles de langage) et l'intelligence artificielle pour la science (par exemple, la santé, la science des matériaux et la radiologie).

Étudiants actuels

Publications

Sparsity-Aware Evolution for Model Merging
Huan Zhang
Yanjian Zhang
Nadi Tomeh
Guillaume Wisniewski
Bang Liu
We propose a sparsity-aware evolutionary (SAE) framework for model merging that involves iterative pruning-merging cycles to act as a novel … (voir plus)mutation operator. We incorporate the sparsity constraints into the score function, which steers the evolutionary process to favor more sparse models, in addition to other conventional performance scores. Interestingly, the by-product of \textit{competition} for sparsity introduces an extra local \textit{attraction} and interplay into the evolutionary process: if one competitor has more zero elements, the other competitor's non-zero elements will occupy those positions, even though the less sparse competitor loses to the more sparse competitor in other positions. The proposed pipeline is evaluated on a variety of large-scale LLM benchmarks. Experiments demonstrate that our approach can improve model merging reliability across multiple benchmarks, and is easy to incorporate due to its simplicity and being orthogonal to most existing approaches.
2026-02-08
arXiv (prépublication)
doi.org
arxiv.org
AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
Jianhao Ruan
Zhihao Xu
Yiran Peng
Fashen Ren
Zhaoyang Yu
Xinbing Liang
Jinyu Xiang
Yongru Chen
Bang Liu
Chenglin Wu
Yuyu Luo
Jiayi Zhang
Language agents have shown strong promise for task automation. Realizing this promise for increasingly complex, long-horizon tasks has drive… (voir plus)n the rise of a sub-agent-as-tools paradigm for multi-turn task solving. However, existing designs still lack a dynamic abstraction view of sub-agents, thereby hurting adaptability. We address this challenge with a unified, framework-agnostic agent abstraction that models any agent as a tuple Instruction, Context, Tools, Model. This tuple acts as a compositional recipe for capabilities, enabling the system to spawn specialized executors for each task on demand. Building on this abstraction, we introduce an agentic system AOrchestra, where the central orchestrator concretizes the tuple at each step: it curates task-relevant context, selects tools and models, and delegates execution via on-the-fly automatic agent creation. Such designs enable reducing human engineering efforts, and remain framework-agnostic with plug-and-play support for diverse agents as task executors. It also enables a controllable performance-cost trade-off, allowing the system to approach Pareto-efficient. Across three challenging benchmarks (GAIA, SWE-Bench, Terminal-Bench), AOrchestra achieves 16.28% relative improvement against the strongest baseline when paired with Gemini-3-Flash. The code is available at: https://github.com/FoundationAgents/AOrchestra
2026-02-02
arXiv (prépublication)
doi.org
arxiv.org
Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts
Wei Zhou
Hong Huang
Ruize Shi
Bang Liu
Heterogeneous Graph Neural Networks(HGNNs) have advanced mainly through better encoders, yet their decoding/projection stage still relies on… (voir plus) a single shared linear head, assuming it can map rich node embeddings to labels. We call this the Linear Projection Bottleneck: in heterogeneous graphs, contextual diversity and long-tail shifts make a global head miss fine semantics, overfit hub nodes, and underserve tail nodes. While Mixture-of-Experts(MoE) could help, naively applying it clashes with structural imbalance and risks expert collapse. We propose a Heterogeneous-aware Orthogonal Prototype Experts framework named HOPE, a plug-and-play replacement for the standard prediction head. HOPE uses learnable prototype-based routing to assign instances to experts by similarity, letting expert usage follow the natural long-tail distribution, and adds expert orthogonalization to encourage diversity and prevent collapse. Experiments on four real datasets show consistent gains across SOTA HGNN backbones with minimal overhead.
2026-01-08
arXiv (prépublication)
doi.org
arxiv.org
Evolving Programmatic Skill Networks
Haochen Shi
Xingdi Yuan
Bang Liu
We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding libra… (voir plus)ry of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are executable symbolic programs forming a compositional network that evolves through experience. PSN defines three core mechanisms instantiated via large language models: (1)REFLECT for structured fault localization over skill compositions, (2) progressive optimization with maturity-aware update gating that stabilizes reliable skills while maintaining plasticity for uncertain ones, and (3) canonical structural refactoring under rollback validation that maintains network compactness. We further show that PSN's learning dynamics exhibit structural parallels to neural network training. Experiments on MineDojo and Crafter demonstrate robust skill reuse, rapid adaptation, and strong generalization across open-ended task distributions.\footnote{We plan to open-source the code.
2026-01-06
arXiv (prépublication)
doi.org
arxiv.org
GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks
Hao Xu
Xiangru Jian
Xinjian Zhao
Wei Pang
Chao Zhang
Suyuchen Wang
Qixin Zhang
Zhengyuan Dong
Joao Monteiro
Bang Liu
Qiuzhuang Sun
Tianshu Yu
This paper introduces GraphOmni, a comprehensive benchmark designed to evaluate the reasoning capabilities of LLMs on graph-theoretic tasks … (voir plus)articulated in natural language. GraphOmni spans diverse graph types, serialization formats, and prompting schemes, substantially extending upon prior efforts in both scope and depth. Through systematic evaluation, we uncover critical interactions among these dimensions, revealing their decisive impact on model performance. Our experiments show that state-of-the-art closed-source models such as Claude-3.5 and o4-mini consistently lead overall, yet still leave considerable headroom, while open-source models display pronounced sensitivity to various design choices. Beyond the standard scope, larger graphs, real-world graphs, and additional NP-hard tasks are further discussed. We further analyze efficiency via output token usage, highlighting cost–accuracy trade-offs, and introduce a reinforcement learning-based optimizer that adaptively selects factor combinations, reducing evaluation cost by 75\% while retaining strong accuracy. This flexible and extensible benchmark not only deepens understanding of LLM performance on structured graph reasoning but also establishes a robust foundation for advancing model design and evaluation. The code and datasets are available at https://anonymous.4open.science/r/ID-14092.
2025-12-31
International Conference on Learning Representations (Accept (Poster))
doi.org
openreview.net
Towards Agentic Intelligence for Materials Science
Huan Zhang
Yizhan Li
Wenhao Huang
Ziyu Hou
Yu Song
Xuye Liu
Farshid Effaty
Jinya Jiang
Sifan Wu
Qianggang Ding
Izumi Takahara
Leonard R. MacGillivray
Teruyasu Mizoguchi
Tianshu Yu
Lizi Liao
Yuyu Luo
Yu Rong
Jia LI
Ying Diao
Heng Ji … (voir 1 de plus)
Bang Liu
The convergence of artificial intelligence and materials science presents a transformative opportunity, but achieving true acceleration in d… (voir plus)iscovery requires moving beyond task-isolated, fine-tuned models toward agentic systems that plan, act, and learn across the full discovery loop. This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining, through domain adaptation and instruction tuning, to goal-conditioned agents interfacing with simulation and experimental platforms. Unlike prior reviews, we treat the entire process as an end-to-end system to be optimized for tangible discovery outcomes rather than proxy benchmarks. This perspective allows us to trace how upstream design choices-such as data curation and training objectives-can be aligned with downstream experimental success through effective credit assignment. To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science. We then analyze the field through two focused lenses: From the AI perspective, the survey details LLM strengths in pattern recognition, predictive analytics, and natural language processing for literature mining, materials characterization, and property prediction; from the materials science perspective, it highlights applications in materials design, process optimization, and the acceleration of computational workflows via integration with external tools (e.g., DFT, robotic labs). Finally, we contrast passive, reactive approaches with agentic design, cataloging current contributions while motivating systems that pursue long-horizon goals with autonomy, memory, and tool use. This survey charts a practical roadmap towards autonomous, safety-aware LLM agents aimed at discovering novel and useful materials.
2025-12-31
arXiv (prépublication)
doi.org
arxiv.org
Accelerated Inorganic Materials Design with Generative Al Agents
Izumi Takahara
Teruyasu Mizoguchi
Bang Liu
Designing inorganic crystalline materials with tailored properties is critical to technological innovation, yet current generative computati… (voir plus)onal methods often struggle to efficiently explore desired targets with sufficient interpretability. Here, we present MatAgent, a generative approach for inorganic materials discovery that harnesses the powerful reasoning capabilities of large language models (LLMs). By combining a diffusion-based generative model for crystal structure estimation with a predictive model for property evaluation, MatAgent uses iterative, feedback-driven guidance to steer material exploration precisely toward user-defined targets. Integrated with external cognitive tools-including short-term memory, long-term memory, the periodic table, and a comprehensive materials knowledge base-MatAgent emulates human expert reasoning to vastly expand the accessible compositional space. Our results demonstrate that MatAgent robustly directs exploration toward desired properties while consistently achieving high compositional validity, uniqueness, and material novelty. This framework thus provides a highly interpretable, practical, and versatile AI-driven solution to accelerate the discovery and design of next-generation inorganic materials.
2025-11-30
Cell Reports Physical Science (publié)
doi.org
arxiv.org
Improving GUI Grounding with Explicit Position-to-Coordinate Mapping
Suyuchen Wang
Tianyu Zhang
Ahmed Masry
Christopher Pal
Spandana Gella
Bang Liu
Perouz Taslakian
2025-10-02
ArXiv (prépublication)
doi.org
arxiv.org
Accelerated Inorganic Materials Design with Generative AI Agents
Izumi Takahara
Teruyasu Mizoguchi
Bang Liu
2025-09-19
NeurIPS.cc/2025/Workshop/AI4Mat (poster)
openreview.net
openreview.net
Concept-based Steering of Large Language Models for Conditional Molecular Generation
Jeremy Qin
Rushil Gupta
Boris Knyazev
Yang Zhang
Glen Berseth
Bang Liu
Modern LLMs, with their internet-scale pretraining and advanced human-level capabilities across specialized tasks, have demonstrated promisi… (voir plus)ng performance in molecular discovery using existing text-based molecular representations, such as SMILES and SELFIES. However, generating valid, unique, and high-fidelity molecules while precisely controlling for multiple properties simultaneously remains challenging. While prior works demonstrated success by fine-tuning language models on a novel corpus of molecules with property-conditioned tags, real-world applications require generating molecules from diverse property distributions, previously unseen in the training data. To this end, we present Concept-based Activation STeering (CAST), the first approach to apply activation steering to directly edit a model's internal representation for conditional molecular generation. CAST offers a lightweight, flexible alternative to fine-tuning by computing property-conditioned steering vectors via a concept network that does not require retraining the LLM. Through extensive experiments on datasets such as Therapeutics Data Commons, we show that CAST consistently outperforms existing methods on both in-distribution and out-of-distribution conditional generation tasks. We also conduct comprehensive ablation studies to highlight the extent of control our concept-guided steering provides on the molecules generated by the LLM.
2025-09-19
NeurIPS.cc/2025/Workshop/AI4Mat (poster)
openreview.net
openreview.net
System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
Xiaoqiang Wang
Suyuchen Wang
Yun Zhu
Bang Liu
Chain-of-thought (CoT) reasoning enables large language models (LLMs) to move beyond fast System-1 responses and engage in deliberative Syst… (voir plus)em-2 reasoning. However, this comes at the cost of significant inefficiency due to verbose intermediate output. Recent latent-space reasoning methods improve efficiency by operating on hidden states without decoding into language, yet they treat all steps uniformly, failing to distinguish critical deductions from auxiliary steps and resulting in suboptimal use of computational resources. In this paper, we propose System-1.5 Reasoning, an adaptive reasoning framework that dynamically allocates computation across reasoning steps through shortcut paths in latent space. Specifically, System-1.5 Reasoning introduces two types of dynamic shortcuts. The model depth shortcut (DS) adaptively reasons along the vertical depth by early exiting non-critical tokens through lightweight adapter branches, while allowing critical tokens to continue through deeper Transformer layers. The step shortcut (SS) reuses hidden states across the decoding steps to skip trivial steps and reason horizontally in latent space. Training System-1.5 Reasoning involves a two-stage self-distillation process: first distilling natural language CoT into latent-space continuous thought, and then distilling full-path System-2 latent reasoning into adaptive shortcut paths (System-1.5 Reasoning). Experiments on reasoning tasks demonstrate the superior performance of our method. For example, on GSM8K, System-1.5 Reasoning achieves reasoning performance comparable to traditional CoT fine-tuning methods while accelerating inference by over 20x and reducing token generation by 92.31% on average.
2025-09-17
NeurIPS.cc/2025/Conference (poster)
doi.org
openreview.net
R3Mem: Bridging Memory Retention and Retrieval via Reversible Compression.
Xiaoqiang Wang 0007
Suyuchen Wang
Yun Zhu
Bang Liu
2025-08-26
DBLP.org (inconnu)
openreview.net
openreview.net