118 citations · 169 across the 35 of their papers we have counts for
38 papers
Causes of Hot Jupiter Inflation from Causal Discovery
Zehao Jin, Mohamad Ali-Dib, Yujia Zheng +3
Hot Jupiters often have radii larger than predicted by standard cooling--contraction models, but it remains unclear which process supplies or preserves the extra internal heat. We…
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…
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Fan Feng, Selena Ge, Minghao Fu +6
Recent work has framed decision-making as a sequence modeling problem using generative models such as diffusion models. Although promising, these approaches often overlook latent f…
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…
A General Representation-Based Approach to Multi-Source Domain Adaptation
Ignavier Ng, Yan Li, Zijian Li +3
A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle high-dimensional observatio…
Diverse Dictionary Learning
Yujia Zheng, Zijian Li, Shunxing Fan +2
Given only observational data , where both the latent variables and the generating process are unknown, recovering is ill-posed without additional assumptions…
ParamMem: Augmenting Language Agents with Parametric Reflective Memory
Tianjun Yao, Yongqiang Chen, Yujia Zheng +3
Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to ad…
Emerging from Ground: Addressing Intent Deviation in Tool-Using Agents via Deriving Real Calls into Virtual Trajectories
Qian Xiong, Yuekai Huang, Bo Yang +7
LLMs have advanced tool-using agents for real-world applications, yet they often lead to unexpected behaviors or results. Beyond obvious failures, the subtle issue of "intent devia…
Higher-Order Causal Structure Learning with Additive Models
James Enouen, Yujia Zheng, Ignavier Ng +2
Causal structure learning has long been the central task of inferring causal insights from data. Despite the abundance of real-world processes exhibiting higher-order mechanisms, h…
Thought Communication in Multiagent Collaboration
Yujia Zheng, Zhuokai Zhao, Zijian Li +4
Natural language has long enabled human cooperation, but its lossy, ambiguous, and indirect nature limits the potential of collective intelligence. While machines are not subject t…
Understanding Catastrophic Interference: On the Identifibility of Latent Representations
Yuke Li, Yujia Zheng, Tianyi Xiong +2
Catastrophic interference, also known as catastrophic forgetting, is a fundamental challenge in machine learning, where a trained learning model progressively loses performance on…
A Survey of Vibe Coding with Large Language Models
Yuyao Ge, Lingrui Mei, Zenghao Duan +12
The advancement of large language models (LLMs) has catalyzed a paradigm shift from code generation assistance to autonomous coding agents, enabling a novel development methodology…
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,…
LLM Interpretability with Identifiable Temporal-Instantaneous Representation
Xiangchen Song, Jiaqi Sun, Zijian Li +2
Despite Large Language Models' remarkable capabilities, understanding their internal representations remains challenging. Mechanistic interpretability tools such as sparse autoenco…
Causal evidence for the primordiality of colours in trans-Neptunian objects
Benjamin L. Davis, Mohamad Ali-Dib, Yujia Zheng +3
The origins of the colours of Trans-Neptunian Objects (TNOs) represent a crucial unresolved question, central to understanding the history of our Solar System. Recent observational…
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
Yujia Zheng, Tianhao Li, Haotian Huang +8
Prompt-based adversarial attacks have become an effective means to assess the robustness of large language models (LLMs). However, existing approaches often treat prompts as monoli…
StructSynth: Dependency Graphs as Generation Plans for Low-Data Tabular Synthesis with Language Models
Siyi Liu, Yujia Zheng, Haoyang Li +1
Tabular data derives its value from inter-feature dependencies, yet preserving them during synthesis is fragile when samples are scarce. Existing approaches either learn dependenci…
Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems
Qian Xiong, Yuekai Huang, Ziyou Jiang +4
The emergence of the tool agent paradigm has broadened the capability boundaries of the Large Language Model (LLM), enabling it to complete more complex tasks. However, the effecti…
Causal Evidence for the Primordiality of Colors in Trans-Neptunian Objects
Benjamin L. Davis, Mohamad Ali-Dib, Yujia Zheng +3
The origins of the colors of Trans-Neptunian Objects (TNOs) represent a crucial unresolved question, central to understanding the history of our Solar System. Recent observational…
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…
Causal Discovery of Latent Variables in Galactic Archaeology
Zehao Jin, Yuxi Lu, Yuan-Sen Ting +2
Galactic archaeology--the study of stellar migration histories--provides insights into galaxy formation and evolution. However, establishing causal relationships between observable…
Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
Xiangchen Song, Aashiq Muhamed, Yujia Zheng +5
Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration…
Nonparametric Factor Analysis and Beyond
Yujia Zheng, Yang Liu, Jiaxiong Yao +2
Nearly all identifiability results in unsupervised representation learning inspired by, e.g., independent component analysis, factor analysis, and causal representation learning, r…
Type Information-Assisted Self-Supervised Knowledge Graph Denoising
Jiaqi Sun, Yujia Zheng, Xinshuai Dong +2
Knowledge graphs serve as critical resources supporting intelligent systems, but they can be noisy due to imperfect automatic generation processes. Existing approaches to noise det…