Author name cluster

Xintong Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

AAAI Conference 2026 Conference Paper

Spatio-Temporal Hierarchical Causal Models

Xintong Li
Haoran Zhang
Xiao Zhou

The abundance of fine-grained spatio-temporal data, such as traffic sensor networks, offers vast opportunities for scientific discovery. However, inferring causal relationships from such observational data remains challenging, particularly due to unobserved confounders that are specific to units (e.g., geographical locations) yet influence outcomes over time. Most existing methods for spatio-temporal causal inference assume that all confounders are observed, an assumption that is often violated in practice. In this paper, we introduce Spatio-Temporal Hierarchical Causal Models (ST-HCMs), a novel graphical framework that extends hierarchical causal modeling to the spatio-temporal domain. At the core of our approach is the Spatio-Temporal Collapse Theorem, which shows that a complex ST-HCM converges to a simpler flat causal model as the amount of subunit data increases. This theoretical result enables a general procedure for causal identification, allowing ST-HCMs to recover causal effects even in the presence of unobserved, time-invariant unit-level confounders, a scenario where standard non-hierarchical models fail. We validate the effectiveness of our framework on both synthetic and real-world datasets, demonstrating its potential for robust causal inference in complex dynamic systems.

PDF Details DOI

AAAI Conference 2025 Conference Paper

FAP-CD: Fairness-Driven Age-Friendly Community Planning via Conditional Diffusion Generation

Jinlin Li
Xintong Li
Xiao Zhou

As global populations age rapidly, incorporating age-specific considerations into urban planning has become essential to addressing the urgent demand for age-friendly built environments and ensuring sustainable urban development. However, current practices often overlook these considerations, resulting in inadequate and unevenly distributed elderly services in cities. There is a pressing need for equitable and optimized urban renewal strategies to support effective age-friendly planning. To address this challenge, we propose a novel framework, Fairness-driven Age-friendly community Planning via Conditional Diffusion generation (FAP-CD). FAP-CD leverages a conditioned graph denoising diffusion probabilistic model to learn the joint probability distribution of aging facilities and their spatial relationships at a fine-grained regional level. Our framework generates optimized facility distributions by iteratively refining noisy graphs, conditioned on the needs of the elderly during the diffusion process. Key innovations include a demand-fairness pre-training module that integrates community demand features and facility characteristics using an attention mechanism and min-max optimization, ensuring equitable service distribution across regions. Additionally, a discrete graph structure captures walkable accessibility within regional road networks, guiding model sampling. To enhance information integration, we design a graph denoising network with an attribute augmentation module and a hybrid graph message aggregation module, combining local and global node and edge information. Empirical results across multiple metrics demonstrate the effectiveness of FAP-CD in balancing age-friendly needs with regional equity, achieving an average improvement of 41% over competitive baseline models.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Geometry-Aware Adaptation for Pretrained Models

Nicholas Roberts
Xintong Li
Dyah Adila
Sonia Cromp
Tzu-Heng Huang
Jitian Zhao
Frederic Sala

Machine learning models---including prominent zero-shot models---are often trained on datasets whose labels are only a small proportion of a larger label space. Such spaces are commonly equipped with a metric that relates the labels via distances between them. We propose a simple approach to exploit this information to adapt the trained model to reliably predict new classes---or, in the case of zero-shot prediction, to improve its performance---without any additional training. Our technique is a drop-in replacement of the standard prediction rule, swapping $\text{argmax}$ with the Fréchet mean. We provide a comprehensive theoretical analysis for this approach, studying (i) learning-theoretic results trading off label space diameter, sample complexity, and model dimension, (ii) characterizations of the full range of scenarios in which it is possible to predict any unobserved class, and (iii) an optimal active learning-like next class selection procedure to obtain optimal training classes for when it is not possible to predict the entire range of unobserved classes. Empirically, using easily-available external metrics, our proposed approach, Loki, gains up to 29. 7% relative improvement over SimCLR on ImageNet and scales to hundreds of thousands of classes. When no such metric is available, Loki can use self-derived metrics from class embeddings and obtains a 10. 5% improvement on pretrained zero-shot models such as CLIP.

PDF Details

ICML Conference 2022 Conference Paper

A 3 T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing

He Bai 0002
Renjie Zheng
Jun-Kun Chen
Mingbo Ma
Xintong Li
Liang Huang 0001

Recently, speech representation learning has improved many speech-related tasks such as speech recognition, speech classification, and speech-to-text translation. However, all the above tasks are in the direction of speech understanding, but for the inverse direction, speech synthesis, the potential of representation learning is yet to be realized, due to the challenging nature of generating high-quality speech. To address this problem, we propose our framework, Alignment-Aware Acoustic-Text Pretraining (A$^3$T), which reconstructs masked acoustic signals with text input and acoustic-text alignment during training. In this way, the pretrained model can generate high quality reconstructed spectrogram, which can be applied to the speech editing and unseen speaker TTS directly. Experiments show A$^3$T outperforms SOTA models on speech editing, and improves multi-speaker speech synthesis without the external speaker verification model.

Details

NeurIPS Conference 2022 Conference Paper

AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels

Nicholas Roberts
Xintong Li
Tzu-Heng Huang
Dyah Adila
Spencer Schoenberg
Cheng-Yu Liu
Lauren Pick
Haotian Ma

Weak supervision (WS) is a powerful method to build labeled datasets for training supervised models in the face of little-to-no labeled data. It replaces hand-labeling data with aggregating multiple noisy-but-cheap label estimates expressed by labeling functions (LFs). While it has been used successfully in many domains, weak supervision's application scope is limited by the difficulty of constructing labeling functions for domains with complex or high-dimensional features. To address this, a handful of methods have proposed automating the LF design process using a small set of ground truth labels. In this work, we introduce AutoWS-Bench-101: a framework for evaluating automated WS (AutoWS) techniques in challenging WS settings---a set of diverse application domains on which it has been previously difficult or impossible to apply traditional WS techniques. While AutoWS is a promising direction toward expanding the application-scope of WS, the emergence of powerful methods such as zero-shot foundation models reveal the need to understand how AutoWS techniques compare or cooperate with modern zero-shot or few-shot learners. This informs the central question of AutoWS-Bench-101: given an initial set of 100 labels for each task, we ask whether a practitioner should use an AutoWS method to generate additional labels or use some simpler baseline, such as zero-shot predictions from a foundation model or supervised learning. We observe that it is necessary for AutoWS methods to incorporate signal from foundation models if they are to outperform simple few-shot baselines, and AutoWS-Bench-101 promotes future research in this direction. We conclude with a thorough ablation study of AutoWS methods.

PDF Details

YNIMG Journal 2021 Journal Article

The effect of eye gaze direction on emotional mimicry: A multimodal study with electromyography and electroencephalography

Beibei Kuang
Xueting Li
Xintong Li
Mingxiao Lin
Shanrou Liu
Ping Hu

Emotional mimicry plays an important role in social interaction and is influenced by social context, especially eye gaze direction. However, the neural mechanism underlying the effect of eye gaze direction on emotional mimicry is unclear. Here, we explored how eye gaze direction influenced emotional mimicry with a combination of electromyography (EMG) and electroencephalography (EEG) techniques, which may provide a more comprehensive measure. To do this, we recorded facial EMG and scalp EEG signals simultaneously while participants observed emotional faces (happy vs. angry) with direct or averted gaze. Then, we split the EEG trials into two mimicry intensity categories (high mimicry intensity, HMI vs. low mimicry intensity, LMI) according to EMG activity. The ERP difference between HMI and LMI EEG trials revealed four ERP components (P50, P150, N200 and P300), and the effect of eye gaze direction on emotional mimicry was prominent on P300 at P7 and P8. Moreover, we also observed differences in the effect of eye gaze direction on mimicry of happy faces and angry faces, which were found on P300 at P7, as well as P150 at P7 and N200 at P7 and Pz. In short, the present study isolated the neural signals of emotional mimicry with a new multimodal method, and provided empirical neural evidence that eye gaze direction affected emotional mimicry.

Details DOI