12 citations · 39 across the 42 of their papers we have counts for
31 papers · 1 filter
Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models
Zijian Li, Ruichu Cai, Feng Xie +7
Uncovering latent variables and their causal relations from observed data is a fundamental yet challenging problem. Existing methods often rely on restrictive assumptions, such as…
Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
Fan Feng, Yujia Zheng, Minghao Fu +5
Learning and planning in imagination using world models provides an effective paradigm for training agents for decision-making. However, existing approaches often rely on high-dime…
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
Lingjing Kong, Xin Liu, Guangyi Chen +9
Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into…
AIMER: Calibration-Free Task-Agnostic MoE Expert Pruning
Zongfang Liu, Guangyi Chen, Shengkun Tang +3
Mixture-of-Experts (MoE) language models increase parameter capacity without proportional per-token computation, yet deployment still requires storing the full expert pool, making…
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…
Towards Identifiability of Hierarchical Temporal Causal Representation Learning
Zijian Li, Minghao Fu, Junxian Huang +5
Modeling hierarchical latent dynamics behind time series data is critical for capturing temporal dependencies across multiple levels of abstraction in real-world tasks. However, ex…
Online Time Series Forecasting with Theoretical Guarantees
Zijian Li, Changze Zhou, Minghao Fu +6
This paper is concerned with online time series forecasting, where unknown distribution shifts occur over time, i.e., latent variables influence the mapping from historical to futu…
CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations
Guangyi Chen, Yunlong Deng, Peiyuan Zhu +4
Causal Representation Learning (CRL) aims to uncover the data-generating process and identify the underlying causal variables and relations, whose evaluation remains inherently cha…
Characterization and Learning of Causal Graphs with Latent Confounders and Post-treatment Selection from Interventional Data
Gongxu Luo, Loka Li, Guangyi Chen +2
Interventional causal discovery seeks to identify causal relations by leveraging distributional changes introduced by interventions, even in the presence of latent confounders. Bey…
PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits
Loka Li, Wong Yu Kang, Minghao Fu +7
Understanding human behavior traits is central to applications in human-computer interaction, computational social science, and personalized AI systems. Such understanding often re…
Should Bias be Eliminated? A General Framework to Use Bias for OOD Generalization
Yan Li, Yunlong Deng, Zijian Li +4
Most approaches to out-of-distribution (OOD) generalization learn domain-invariant representations by discarding contextual bias. In this paper, we raise a critical question: Shoul…
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…
Towards Understanding Extrapolation: a Causal Lens
Lingjing Kong, Guangyi Chen, Petar Stojanov +3
Canonical work handling distribution shifts typically necessitates an entire target distribution that lands inside the training distribution. However, practical scenarios often inv…
Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis
Minghao Fu, Biwei Huang, Zijian Li +5
Understanding climate dynamics requires going beyond correlations in observational data to uncover the underlying causal process. Latent drivers such as atmospheric processes play…
Causal Representation Learning from Multimodal Biomedical Observations
Yuewen Sun, Lingjing Kong, Guangyi Chen +10
Prevalent in biomedical applications (e.g., human phenotype research), multimodal datasets can provide valuable insights into the underlying physiological mechanisms. However, curr…
Causal Temporal Representation Learning with Nonstationary Sparse Transition
Xiangchen Song, Zijian Li, Guangyi Chen +4
Causal Temporal Representation Learning (Ctrl) methods aim to identify the temporal causal dynamics of complex nonstationary temporal sequences. Despite the success of existing Ctr…
Continual Learning of Nonlinear Independent Representations
Boyang Sun, Ignavier Ng, Guangyi Chen +3
Identifying the causal relations between interested variables plays a pivotal role in representation learning as it provides deep insights into the dataset. Identifiability, as the…
MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification
Tianjun Yao, Jiaqi Sun, Defu Cao +2
Recent works have introduced GNN-to-MLP knowledge distillation (KD) frameworks to combine both GNN's superior performance and MLP's fast inference speed. However, existing KD frame…
Learning Discrete Concepts in Latent Hierarchical Models
Lingjing Kong, Guangyi Chen, Biwei Huang +3
Learning concepts from natural high-dimensional data (e.g., images) holds potential in building human-aligned and interpretable machine learning models. Despite its encouraging pro…
From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals
Ruichu Cai, Zhifang Jiang, Zijian Li +6
Existing methods for multi-modal time series representation learning aim to disentangle the modality-shared and modality-specific latent variables. Although achieving notable perfo…
On the Identification of Temporally Causal Representation with Instantaneous Dependence
Zijian Li, Yifan Shen, Kaitao Zheng +5
Temporally causal representation learning aims to identify the latent causal process from time series observations, but most methods require the assumption that the latent causal p…
Federated Causal Discovery from Heterogeneous Data
Loka Li, Ignavier Ng, Gongxu Luo +5
Conventional causal discovery methods rely on centralized data, which is inconsistent with the decentralized nature of data in many real-world situations. This discrepancy has moti…
Nonstationary Time Series Forecasting via Unknown Distribution Adaptation
Zijian Li, Ruichu Cai, Zhenhui Yang +6
As environments evolve, temporal distribution shifts can degrade time series forecasting performance. A straightforward solution is to adapt to nonstationary changes while preservi…