Bang Liu

Biography

Bang Liu is an assistant professor in the Department of Computer Science and Operations Research (DIRO), and a core member of the Applied Research in Computational Linguistics Lab (RALI) at Université de Montréal. He is also an associate academic member of Mila – Quebec Artificial Intelligence Institute and a Canada CIFAR AI Chair.

Liu received his BEng from the University of Science and Technology of China in 2013, and his MSc and PhD degrees from the University of Alberta in 2015 and 2020, respectively. His research interests lie primarily in the areas of natural language processing, multimodal and embodied learning, theory and techniques for AGI (e.g., understanding and improving large language models), and AI for science (e.g., health, material science, XR).

Current Students

Qianggang Ding

PhD - Université de Montréal

Farshid Effaty

Postdoctorate - Université de Montréal

Wenhao Huang

PhD - Université de Montréal

Yizhan Li

PhD - Université de Montréal

Kyle Roth

PhD - Université de Montréal

Haochen Shi

PhD - Université de Montréal

Xiran Song

PhD - Université de Montréal

PhD - Université de Montréal

PhD - Université de Montréal

Sifan Wu

PhD - Université de Montréal

Dekun Wu

PhD - Université de Montréal

Huan Zhang

Master's Research - Université de Montréal

Revolutionizing Materials Science with NLP: Introducing MatSci-NLP and HoneyBee

Armin Zolfagharidariani

Master's Research - Université de Montréal

Github

Blog Posts

MatSci-Instruct and HoneyBee training workflow.

October 21, 2024

Bang Liu

Read the article

Publications

What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles

Mi Zhou

Sifan Wu

H. Zhang

Qi Sima

We investigate the capacity of Large Language Models (LLMs) for imaginative reasoning—the proactive construction, testing, and revision of… (see more) hypotheses in information-sparse environments. Existing benchmarks, often static or focused on social deduction, fail to capture the dynamic, exploratory nature of this reasoning process. To address this gap, we introduce a comprehensive research framework based on the classic "Turtle Soup" game, integrating a benchmark, an agent, and an evaluation protocol. We present TurtleSoup-Bench, the first large-scale, bilingual, interactive benchmark for imaginative reasoning, comprising 800 turtle soup stories sourced from both the Internet and expert authors. We also propose Mosaic-Agent, a novel agent designed to assess LLMs' performance in this setting. To evaluate reasoning quality, we develop a multi-dimensional protocol measuring logical consistency, detail completion, and conclusion alignment. Experiments with leading LLMs reveal clear capability limits, common failure patterns, and a significant performance gap compared to humans. Our work offers new insights into LLMs' imaginative reasoning and establishes a foundation for future research on exploratory agent behavior.

2026-03-13

AAAI Conference on Artificial Intelligence (published)

arxiv.org

Accelerated Inorganic Materials Design with Generative Al Agents

Izumi Takahara

Teruyasu Mizoguchi

Designing inorganic crystalline materials with tailored properties is critical to technological innovation, yet current generative computati… (see more)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 (published)

arxiv.org

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping

Christopher Pal

2025-09-30

arXiv (published)

arxiv.org

Accelerated Inorganic Materials Design with Generative AI Agents

Izumi Takahara

Teruyasu Mizoguchi

2025-09-19

NeurIPS.cc/2025/Workshop/AI4Mat (poster)

Concept-based Steering of Large Language Models for Conditional Molecular Generation

Yang Zhang

Modern LLMs, with their internet-scale pretraining and advanced human-level capabilities across specialized tasks, have demonstrated promisi… (see more)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)

System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts

Xiaoqiang Wang

Suyuchen Wang

Yun Zhu

Chain-of-thought (CoT) reasoning enables large language models (LLMs) to move beyond fast System-1 responses and engage in deliberative Syst… (see more)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)

R3Mem: Bridging Memory Retention and Retrieval via Reversible Compression.

Xiaoqiang Wang 0007

Suyuchen Wang

Yun Zhu

2025-08-26

DBLP.org (unknown)

LLMs for Experiment Design in Scientific Domains: Are We There Yet?

Rushil Gupta

Jason Hartford

2025-06-10

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

Improving Context Fidelity via Native Retrieval-Augmented Reasoning

Suyuchen Wang

Jinlin Wang

Xinyu Wang

Shiqi Li

Xiangru Tang

Sirui Hong

Xiao-Wen Chang

Chenglin Wu

Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on prov… (see more)ided information. Existing approaches either rely on expensive supervised fine-tuning to generate evidence post-answer or train models to perform web searches without necessarily improving utilization of the given context. We propose CARE, a novel native retrieval-augmented reasoning framework that teaches LLMs to explicitly integrate in-context evidence within their reasoning process with the model's own retrieval capabilities. Our method requires minimal labeled evidence data while significantly enhancing both retrieval accuracy and answer generation performance through strategically retrieved in-context tokens in the reasoning chain. Extensive experiments on multiple real-world and counterfactual QA benchmarks demonstrate that our approach substantially outperforms supervised fine-tuning, traditional retrieval-augmented generation methods, and external retrieval solutions. This work represents a fundamental advancement in making LLMs more accurate, reliable, and efficient for knowledge-intensive tasks.

2025-06-08

ICML.cc/2025/Workshop/LCFM (accepted)

DASFormer: self-supervised pretraining for earthquake monitoring

Qianggang Ding

Zhichao Shen

Weiqiang Zhu

Earthquake monitoring is a fundamental task to unravel the underlying physics of earthquakes and mitigate associated hazards for public safe… (see more)ty. Distributed acoustic sensing, or DAS, which transforms pre-existing telecommunication cables into ultra-dense seismic networks, offers a cost-effective and scalable solution for next-generation earthquake monitoring. However, current approaches for earthquake monitoring like PhaseNet and PhaseNet-2 primarily rely on supervised learning, while manually labeled DAS data is quite limited and it is difficult to obtain more annotated datasets. In this paper, we present DASFormer, a novel self-supervised pretraining technique on DAS data with a coarse-to-fine framework that models spatial-temporal signal correlation. We treat earthquake monitoring as an anomaly detection task and demonstrate DASFormer can be directly utilized as a seismic phase detector. Experimental results demonstrate that DASFormer is effective in terms of several evaluation metrics and outperforms state-of-the-art time-series forecasting, anomaly detection, and foundation models on the unsupervised seismic detection task. We also demonstrate the potential of fine-tuning DASFormer to downstream tasks through case studies.

2025-03-05

ICLR.cc/2025/Workshop/FM-Wild (published)

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

Juan A. Rodriguez

Chao Wang

Akshay Kalkunte Suresh

Abhay Puri

Xiangru Jian

Pierre-Andre Noel

Sathwik Tejaswi Madhusudhan

Enamul Hoque

Christopher Pal

Issam H. Laradji

David Vázquez

Perouz Taslakian … (see 2 more)

Spandana Gella

Sai Rajeswar

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges… (see more) on having a good connector that maps visual features generated by a vision encoder to a shared embedding space with the LLM while preserving semantic similarity. Existing connectors, such as multilayer perceptrons (MLPs), lack inductive bias to constrain visual features within the linguistic structure of the LLM's embedding space, making them data-hungry and prone to cross-modal misalignment. In this work, we propose a novel vision-text alignment method, AlignVLM, that maps visual features to a weighted average of LLM text embeddings. Our approach leverages the linguistic priors encoded by the LLM to ensure that visual features are mapped to regions of the space that the LLM can effectively interpret. AlignVLM is particularly effective for document understanding tasks, where visual and textual modalities are highly correlated. Our extensive experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods, with larger gains on document understanding tasks and under low-resource setups. We provide further analysis demonstrating its efficiency and robustness to noise.

2025-03-04

ICLR.cc/2025/Workshop/Re-Align (poster)

Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection

Yun Zhu

Jia-Chen Gu

Caitlin Sikora

Ho Ko

Yinxiao Liu

Chu-Cheng Lin

Lei Shu

Liangchen Luo

Lei Meng

Jindong Chen

Large language models (LLMs) augmented with retrieval exhibit robust performance and extensive versatility by incorporating external context… (see more)s. However, the input length grows linearly in the number of retrieved documents, causing a dramatic increase in latency. In this paper, we propose a novel paradigm named Sparse RAG, which seeks to cut computation costs through sparsity. Speciﬁcally, Sparse RAG encodes retrieved documents in parallel, which eliminates latency introduced by long-range attention of retrieved documents. Then, LLMs selectively decode the output by only attending to highly relevant caches auto-regressively, which are chosen via prompting LLMs with special control tokens. It is notable that Sparse RAG combines the assessment of each individual document and the generation of the response into a single process. The designed sparse mechanism in a RAG system can facilitate the reduction of the number of documents loaded during decoding for accelerating the inference of the RAG system. Additionally, ﬁltering out undesirable contexts enhances the model’s focus on relevant context, inherently improving its generation quality. Evaluation results on four datasets show that Sparse RAG can be used to strike an optimal balance between generation quality and computational efﬁciency, demonstrating its generalizability across tasks.

2025-01-21

ICLR.cc/2025/Conference (poster)