1.2k citations · 1.2k across the 23 of their papers we have counts for
26 papers
On Parameters of Nonlinear Scalar Dynamics from Video: Invariants, Calibration, and Identifiability
Wenjie Wang, Yuanyuan Wang, Zixiang Jiang +2
Physical parameter estimation from video aims to recover the parameters of a known family of governing dynamical equations from pixel observations. Existing identifiability theory…
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
Peiyuan Zhu, Shaoan Xie, Zijian Li +5
Contrastive pre-training has propelled video-text alignment, yet models often inherit the critical limitations of their image-text predecessors like CLIP, resulting in entangled re…
Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training
Xiangchen Song, Zhenhao Chen, Lingjing Kong +4
Large language model test-time training (TTT) is often evaluated through local proxy metrics: models are updated on recent tokens, retrieved context, target-domain data, or verifia…
A Dialogue between Causal and Traditional Representation Learning: Toward Mutual Benefits in a Unified Formulation
Yan Li, Yuewen Sun, Shaoan Xie +4
Causal representation learning (CRL) and traditional representation learning have largely developed along different trajectories. Traditional representation learning has been drive…
SEDGE: Structural Extrapolated Data Generation
Kun Zhang, Jiaqi Sun, Yiqing Li +3
This paper aims to address the challenge of data generation beyond the training data and proposes a framework for Structural Extrapolated Data GEneration (SEDGE) based on suitable…
From Generalist to Specialist Representation
Yujia Zheng, Fan Feng, Yuke Li +3
Given a generalist model, learning a task-relevant specialist representation is fundamental for downstream applications. Identifiability, the asymptotic guarantee of recovering the…
The Power of Order: Fooling LLMs with Adversarial Table Permutations
Xinshuai Dong, Haifeng Chen, Xuyuan Liu +5
Large Language Models have achieved remarkable success and are increasingly deployed in critical applications involving tabular data, such as Table Question Answering. However, the…
Causal Representation Learning from General Environments under Nonparametric Mixing
Ignavier Ng, Shaoan Xie, Xinshuai Dong +2
Causal representation learning aims to recover the latent causal variables and their causal relations, typically represented by directed acyclic graphs (DAGs), from low-level obser…
Learning by Analogy: A Causal Framework for Composition Generalization
Lingjing Kong, Shaoan Xie, Yang Jiao +6
Compositional generalization -- the ability to understand and generate novel combinations of learned concepts -- enables models to extend their capabilities beyond limited experien…
Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality
Lingjing Kong, Shaoan Xie, Guangyi Chen +4
Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignmen…
Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards
Shaoan Xie, Lingjing Kong, Xiangchen Song +4
Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement…
Nonparametric Identification of Latent Concepts
Yujia Zheng, Shaoan Xie, Kun Zhang
We are born with the ability to learn concepts by comparing diverse observations. This helps us to understand the new world in a compositional manner and facilitates extrapolation,…
SmartCLIP: Modular Vision-language Alignment with Identification Guarantees
Shaoan Xie, Lingjing Kong, Yujia Zheng +5
Contrastive Language-Image Pre-training (CLIP)~\citep{radford2021learning} has emerged as a pivotal model in computer vision and multimodal learning, achieving state-of-the-art per…
Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning
Zijian Li, Shunxing Fan, Yujia Zheng +6
Disentangled representation learning aims to uncover latent variables underlying the observed data, and generally speaking, rather strong assumptions are needed to ensure identifia…
Controllable Video Generation with Provable Disentanglement
Yifan Shen, Peiyuan Zhu, Zijian Li +6
Controllable video generation remains a significant challenge, despite recent advances in generating high-quality and consistent videos. Most existing methods for controlling video…
Causal Representation Learning from Multiple Distributions: A General Setting
Kun Zhang, Shaoan Xie, Ignavier Ng +1
In many problems, the measured variables (e.g., image pixels) are just mathematical functions of the latent causal variables (e.g., the underlying concepts or objects). For the pur…
DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion Models
Shaoan Xie, Yang Zhao, Zhisheng Xiao +5
This study introduces Text-Guided Subject-Driven Image Inpainting, a novel task that combines text and exemplar images for image inpainting. While both text and exemplar images hav…
Semi-Implicit Denoising Diffusion Models (SIDDMs)
Yanwu Xu, Mingming Gong, Shaoan Xie +4
Despite the proliferation of generative models, achieving fast sampling during inference without compromising sample diversity and quality remains challenging. Existing models such…
Partial Identifiability for Domain Adaptation
Lingjing Kong, Shaoan Xie, Weiran Yao +5
Unsupervised domain adaptation is critical to many real-world applications where label information is unavailable in the target domain. In general, without further assumptions, the…
Advancing Counterfactual Inference through Nonlinear Quantile Regression
Shaoan Xie, Biwei Huang, Bin Gu +2
The capacity to address counterfactual "what if" inquiries is crucial for understanding and making use of causal influences. Traditional counterfactual inference, under Pearls' cou…
Emerging Synergies in Causality and Deep Generative Models: A Survey
Guanglin Zhou, Shaoan Xie, Guang-Yuan Hao +7
In the field of artificial intelligence (AI), the quest to understand and model data-generating processes (DGPs) is of paramount importance. Deep generative models (DGMs) have prov…
SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model
Shaoan Xie, Zhifei Zhang, Zhe Lin +2
Generic image inpainting aims to complete a corrupted image by borrowing surrounding information, which barely generates novel content. By contrast, multi-modal inpainting provides…
Adversarial Consistency for Single Domain Generalization in Medical Image Segmentation
Yanwu Xu, Shaoan Xie, Maxwell Reynolds +3
An organ segmentation method that can generalize to unseen contrasts and scanner settings can significantly reduce the need for retraining of deep learning models. Domain Generaliz…
Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation
Yanwu Xu, Shaoan Xie, Wenhao Wu +3
Unpaired image-to-image translation (I2I) is an ill-posed problem, as an infinite number of translation functions can map the source domain distribution to the target distribution.…