12 citations · 39 across the 42 of their papers we have counts for
47 papers
Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion
Yifan Shen, Yewei Xia, Gongxu Luo +6
Autoregressive video generators synthesize long videos through chunk-wise rollouts, yet they are typically trained to predict only the immediate future. This limited prediction hor…
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…
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…
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…
Unsupervised Synthetic Image Attribution: Alignment and Disentanglement
Zongfang Liu, Guangyi Chen, Boyang Sun +2
As the quality of synthetic images improves, identifying the underlying concepts of model-generated images is becoming increasingly crucial for copyright protection and ensuring mo…
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…
MixAR: Mixture Autoregressive Image Generation
Jinyuan Hu, Jiayou Zhang, Shaobo Cui +2
Autoregressive (AR) approaches, which represent images as sequences of discrete tokens from a finite codebook, have achieved remarkable success in image generation. However, the qu…
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…
Towards Self-Refinement of Vision-Language Models with Triangular Consistency
Yunlong Deng, Guangyi Chen, Tianpei Gu +4
Vision-Language Models (VLMs) integrate visual knowledge with the analytical capabilities of Large Language Models (LLMs) through supervised visual instruction tuning, using image-…
Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
Yunlong Deng, Boyang Sun, Yan Li +4
Due to their inherent complexity, reasoning tasks have long been regarded as rigorous benchmarks for assessing the capabilities of machine learning models, especially large languag…
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…
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…
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…
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…
Reflection-Window Decoding: Text Generation with Selective Refinement
Zeyu Tang, Zhenhao Chen, Xiangchen Song +6
The autoregressive decoding for text generation in large language models (LLMs), while widely used, is inherently suboptimal due to the lack of a built-in mechanism to perform refi…
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…
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…